© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8958
    Prev
    Next
    INDEX
    Explanations

    code snippets, recognizing patterns like bitwise shift operators, conditional operators, string manipulation, and character comparisons.

    oai_token-act-pair · gemini-2.0-flash

    punctuation or 'std'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    IntoConstraints
    -0.74
     MainAxisSize
    -0.69
    ItemBackground
    -0.66
     dataSnapshot
    -0.62
     edelstahl
    -0.61
    principalColumn
    -0.61
     FetchType
    -0.61
     layui
    -0.60
    modb
    -0.59
     Participants
    -0.59
    POSITIVE LOGITS
     '-';
    1.09
     '.';
    1.02
     '*')
    1.02
     '/';
    1.01
     '*':
    1.01
     '-':
    1.00
     '+':
    0.96
     "-";
    0.93
     '/')
    0.93
     '/':
    0.93
    Activations Density 2.279%

    No Known Activations