© 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. 14670
    Prev
    Next
    INDEX
    Explanations

    mentions of finding or discovering something, or something proving to be well.

    oai_token-act-pair · gemini-2.0-flash

    opinions/findings

    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
    ']?>
    -0.56
    '];?>
    -0.54
    \{\\
    -0.52
     útiles
    -0.50
    }]
    -0.48
    BeginContext
    -0.47
    '],
    -0.46
    例文帳に追加
    -0.46
    /*++
    -0.45
    uttavia
    -0.45
    POSITIVE LOGITS
    StatusBadRequest
    0.60
     rectification
    0.59
    Vidite
    0.59
    HasAnnotation
    0.56
     Maulana
    0.54
    ítulo
    0.54
     Shakspeare
    0.54
     baili
    0.53
     primitives
    0.53
     Esc
    0.53
    Activations Density 13.467%

    No Known Activations