© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15954
    Prev
    Next
    INDEX
    Explanations

    recipes and ingredients with a focus on traditional or religious offerings

    oai_token-act-pair · gemini-2.0-flash

    Cooking ingredients and recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Geplaatst
    -0.69
    awtextra
    -0.56
     @"/
    -0.51
    #+#
    -0.48
    mergeFrom
    -0.48
    >';
    -0.47
    }";
    -0.47
    dnn
    -0.47
    unknownFields
    -0.46
    >'+
    -0.45
    POSITIVE LOGITS
     Efq
    0.72
     Sanskrit
    0.68
     steppe
    0.66
     barbati
    0.65
     médié
    0.64
     quæ
    0.63
     Sancho
    0.63
     Mongols
    0.62
     Archivo
    0.61
     Meiji
    0.61
    Activations Density 1.736%

    No Known Activations