© 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. 8286
    Prev
    Next
    INDEX
    Explanations

    a mix of filler words and commentary.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and query structure

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

    Sentences followed by conjunction

    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
     does
    -1.50
     Does
    -1.50
    Does
    -1.45
    does
    -1.26
     doesn
    -1.21
     DOES
    -1.18
     Doesn
    -1.16
    DOES
    -1.11
    Doesn
    -1.11
     did
    -1.05
    POSITIVE LOGITS
    SourceChecksum
    0.79
    enumi
    0.73
    EndContext
    0.60
    Demografie
    0.59
    NotBe
    0.58
    glClear
    0.51
     remise
    0.48
     Deny
    0.47
    setLayout
    0.47
     Estamos
    0.47
    Activations Density 1.257%

    No Known Activations