© 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. 8373
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, punctuation and short words

    oai_token-act-pair · gemini-2.0-flash

    doesn

    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
    ’
    -0.22
    '
    -0.21
     The
    -0.20
    ↵↵
    -0.18
    ;
    -0.18
    )
    -0.18
    .
    -0.17
    /
    -0.16
    :
    -0.15
    ).
    -0.15
    POSITIVE LOGITS
     Arjuna
    0.97
     Esau
    0.97
     photolibrary
    0.93
     doubtnut
    0.93
    extAlignment
    0.93
    出版年
    0.92
     Euphrates
    0.91
    tvguidetime
    0.91
     Moira
    0.90
     Huns
    0.90
    Activations Density 6.673%

    No Known Activations