© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3721
    Prev
    Next
    INDEX
    Explanations

    instances where the word "need" is used for advice or asking something.

    oai_token-act-pair · gemini-2.0-flash

    DIY advice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    K
    -0.58
    [
    -0.57
    S
    -0.53
    C
    -0.51
    I
    -0.50
    -
    -0.49
    T
    -0.48
    â
    -0.47
    R
    -0.47
    ...
    -0.47
    POSITIVE LOGITS
    ValueStyle
    1.20
    LookAnd
    1.19
    ,:);
    1.09
    parsedMessage
    1.09
    EDEFAULT
    1.09
     فريبيس
    1.07
    tonode
    1.06
     विश्वसनीयता
    1.05
    transQ
    1.02
    __(/*!
    1.02
    Activations Density 9.885%

    No Known Activations