© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16340
    Prev
    Next
    INDEX
    Explanations

    code snippets in various programming languages and formats

    oai_token-act-pair · gemini-2.0-flash

    code/markup language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     itſelf
    -0.85
     Theſe
    -0.85
     Efq
    -0.84
     myſelf
    -0.81
     ―――――
    -0.78
     ModelExpression
    -0.77
     ་་
    -0.76
     ſtill
    -0.75
     becauſe
    -0.75
     ――――
    -0.74
    POSITIVE LOGITS
    ds
    0.45
    dd
    0.39
    «
    0.38
    dn
    0.36
    ss
    0.36
    dz
    0.35
    vm
    0.35
    odle
    0.35
    ej
    0.35
    mn
    0.34
    Activations Density 10.193%

    No Known Activations