© 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. 3967
    Prev
    Next
    INDEX
    Explanations

    words related to investigation, claims, and proof

    oai_token-act-pair · gemini-2.0-flash

    Critical statements; disagreement

    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
     MainAxisSize
    -0.91
    UnsafeEnabled
    -0.88
    PerformLayout
    -0.76
     purpoſe
    -0.71
     estimés
    -0.71
     NSCoder
    -0.71
     فريبيس
    -0.70
    ExtendWith
    -0.69
     DialogInterface
    -0.67
     ModelExpression
    -0.67
    POSITIVE LOGITS
    NameInMap
    0.43
    iss
    0.42
    物
    0.42
     L
    0.41
     bother
    0.40
     fac
    0.40
    SST
    0.38
     accept
    0.38
    感情
    0.38
     check
    0.37
    Activations Density 5.213%

    No Known Activations