© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9122
    Prev
    Next
    INDEX
    Explanations

    various prepositions

    oai_token-act-pair · gemini-2.0-flash

    emotional responses and actions

    np_token-act-pair-logits · gpt-4o-mini

    strong emotion/reaction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    aarrggbb
    -0.80
    SourceChecksum
    -0.69
     aapt
    -0.59
    msgTypes
    -0.57
    Geplaatst
    -0.56
     الرياضيه
    -0.56
     externi
    -0.56
    IntoConstraints
    -0.54
    ModelAdmin
    -0.54
    ResumeLayout
    -0.51
    POSITIVE LOGITS
    vägen
    0.69
     concentration
    0.67
     AssemblyTitle
    0.60
     frustration
    0.58
     confusion
    0.58
     صوتيه
    0.57
    concentration
    0.56
    RefNanny
    0.55
    photobucket
    0.55
     response
    0.53
    Activations Density 0.711%

    No Known Activations