© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4201
    Prev
    Next
    INDEX
    Explanations

    references to comedians, comedy, and adjacent concepts

    oai_token-act-pair · gemini-2.0-flash

    comedy and comedians

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    }}}}
    -0.59
    álat
    -0.57
    enterOuterAlt
    -0.54
    }}">
    -0.54
    GeneratedValue
    -0.52
    }],
    -0.52
     "}";
    -0.51
    reeg
    -0.51
     consultato
    -0.50
    igma
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.67
    AndEndTag
    0.52
     صوتيه
    0.50
     ffilmiau
    0.49
     cref
    0.48
    IntoConstraints
    0.46
    例文帳に追加
    0.45
    crunch
    0.44
    abetes
    0.44
    ohar
    0.43
    Activations Density 46.143%

    No Known Activations