© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8600
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" and words that diminish a quality

    oai_token-act-pair · gemini-2.0-flash

    pretty

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Very
    -0.56
     very
    -0.56
     Very
    -0.55
     Очень
    -0.54
    zzleHttp
    -0.51
    الإنجليزية
    -0.49
     essentially
    -0.48
    COUVER
    -0.48
     Extremely
    -0.48
    tersebut
    -0.48
    POSITIVE LOGITS
    migrationBuilder
    0.70
     صوتيه
    0.69
    Atsauces
    0.60
    idopsis
    0.56
    fares
    0.56
     EconPapers
    0.55
    styleType
    0.54
     doInBackground
    0.52
    SuccessListener
    0.52
    öpfer
    0.52
    Activations Density 0.849%

    No Known Activations