© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6509
    Prev
    Next
    INDEX
    Explanations

    various forms of the words "back", "home", "good", "anywhere" and "away", as well as phrases like "so far as" and "on another".

    oai_token-act-pair · gemini-2.0-flash

    Returning/distance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Autoritní
    -0.69
    <bos>
    -0.68
     Paglinawan
    -0.63
     محفوظة
    -0.57
    Vidite
    -0.57
    BufferException
    -0.57
    Diweddarwch
    -0.55
    ContentLoaded
    -0.53
    UnusedPrivate
    -0.52
     Jura
    -0.51
    POSITIVE LOGITS
    antMatchers
    0.56
     zoo
    0.51
     soeur
    0.50
    LETIN
    0.50
    どうか
    0.49
    velt
    0.49
    Respectfully
    0.49
    Anmerkungen
    0.49
     bienvenue
    0.49
    Forked
    0.49
    Activations Density 0.770%

    No Known Activations