© 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. 10274
    Prev
    Next
    INDEX
    Explanations

    code-like structures like class definitions and function calls, possibly across multiple languages

    oai_token-act-pair · gemini-2.0-flash

    Code/programming

    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
    }")
    -1.14
    ")));
    -0.94
    ()]
    -0.91
    ()));
    -0.91
    "]));
    -0.90
    }")
    -0.89
    "],
    -0.89
    '));
    -0.89
    }')
    -0.88
    ]));
    -0.88
    POSITIVE LOGITS
    脚注の使い方
    0.68
    stdc
    0.63
    WireFormatLite
    0.56
    netinet
    0.54
    Hochspringen
    0.53
    APORE
    0.52
    Referencies
    0.52
    Einzelnachweise
    0.52
    المراجع
    0.52
    通販
    0.51
    Activations Density 4.020%

    No Known Activations