© 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. 15901
    Prev
    Next
    INDEX
    Explanations

    phrases that express an opinion or judgement of great value/impact.

    oai_token-act-pair · gemini-2.0-flash

    Political/Strategic moves

    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
    TabIndex
    -0.71
    ValueStyle
    -0.67
     pitié
    -0.63
    antaranya
    -0.63
     nélkül
    -0.60
     aient
    -0.60
     prêtres
    -0.60
     avoient
    -0.59
    prepareStatement
    -0.59
     étoient
    -0.58
    POSITIVE LOGITS
     move
    0.63
    cepan
    0.59
     nod
    0.57
     sop
    0.54
     departure
    0.54
     cur
    0.52
     reach
    0.52
    ListItemIcon
    0.51
     redirection
    0.50
     DEPART
    0.50
    Activations Density 2.067%

    No Known Activations