© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7129
    Prev
    Next
    INDEX
    Explanations

    a wide variety of terms including locations, objects, opinions, and generic words.

    oai_token-act-pair · gemini-2.0-flash

    words related to the concept of frequency or regularity

    np_token-act-pair-logits · gpt-4o-mini

    around

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TestBed
    -0.65
     noastre
    -0.53
    Atsauces
    -0.53
    Configurer
    -0.51
     ModelExpression
    -0.51
    styleUrls
    -0.50
     '\\;'
    -0.48
    ContentAsync
    -0.48
    OrBuilder
    -0.48
    principalTable
    -0.48
    POSITIVE LOGITS
     around
    1.98
     Around
    1.85
    Around
    1.83
    around
    1.76
     AROUND
    1.64
    AROUND
    1.41
     autour
    1.38
     alrededor
    1.37
     intorno
    1.22
     rundt
    1.21
    Activations Density 1.499%

    No Known Activations