© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13245
    Prev
    Next
    INDEX
    Explanations

    mentions of reactions to undesirable situations

    oai_token-act-pair · gemini-2.0-flash

    emotional reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     $_"
    -0.84
    ValueGenerated
    -0.84
     GenerationType
    -0.82
     Theſe
    -0.80
     myſelf
    -0.74
     Monfieur
    -0.73
     Jefus
    -0.73
    tvguidetime
    -0.72
     doubtnut
    -0.72
    ^(@)
    -0.72
    POSITIVE LOGITS
    yntaxException
    0.43
     rep
    0.40
    BeginContext
    0.38
    addGap
    0.37
     oprot
    0.36
    Rep
    0.36
    Geplaatst
    0.36
     justiça
    0.36
     déplacements
    0.35
    rep
    0.34
    Activations Density 23.542%

    No Known Activations