© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10721
    Prev
    Next
    INDEX
    Explanations

    words or phrases that express a value judgement or that are part of conversational filler

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    enumii
    -0.68
    enumi
    -0.64
    出版年
    -0.63
    ();)
    -0.63
    osé
    -0.62
    ]$}
    -0.60
    帖最后由
    -0.59
     Romains
    -0.59
    هن
    -0.58
    jspx
    -0.57
    POSITIVE LOGITS
    ";
    0.68
    ".
    0.64
    ",
    0.63
    '.
    0.60
    ».
    0.59
    ';
    0.59
    }.
    0.59
    }
    0.59
    },
    0.56
    parsedMessage
    0.56
    Activations Density 6.035%

    No Known Activations