© 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. 7833
    Prev
    Next
    INDEX
    Explanations

    references to carrying personal belongings

    oai_token-act-pair · gemini-2.0-flash

    words related to wire organization and management

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

    bags and luggage

    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
    ChildScrollView
    -0.99
    AndEndTag
    -0.87
    UnusedPrivate
    -0.86
    ^(@)
    -0.85
     Efq
    -0.84
    Portale
    -0.84
     <=",
    -0.81
    wiſe
    -0.81
     iſt
    -0.80
    ThroughAttribute
    -0.80
    POSITIVE LOGITS
     cross
    0.52
     du
    0.52
     Car
    0.43
     v
    0.43
     Cross
    0.43
     r
    0.42
     m
    0.41
    反
    0.41
     tr
    0.41
    本
    0.41
    Activations Density 2.195%

    No Known Activations