© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4011
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols within a specific format or context

    oai_token-act-pair · gemini-2.0-flash

    ​​

    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
     avoient
    -0.53
     démocr
    -0.52
     arbete
    -0.50
     financières
    -0.50
     religieuse
    -0.49
     varandra
    -0.48
     étoient
    -0.46
     alimentaire
    -0.46
     chimiques
    -0.46
     skydd
    -0.46
    POSITIVE LOGITS
     the
    0.73
    tagHelperRunner
    0.69
    ".
    0.63
    -
    0.63
     or
    0.63
    )";
    0.60
    NUMX
    0.59
     ​​
    0.59
    afficheront
    0.59
     OR
    0.58
    Activations Density 17.474%

    No Known Activations