© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11244
    Prev
    Next
    INDEX
    Explanations

    code snippets in various languages

    oai_token-act-pair · gemini-2.0-flash

    args

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     }{\
    -0.59
     _
    -0.58
     compagn
    -0.57
    styleType
    -0.57
    new
    -0.56
    M
    -0.56
    minal
    -0.55
    two
    -0.54
    R
    -0.53
    ante
    -0.52
    POSITIVE LOGITS
    PerformLayout
    0.82
     doubtnut
    0.75
    Cordialement
    0.75
    awancara
    0.74
     myſelf
    0.72
    arakhand
    0.71
    <bos>
    0.71
     Fulda
    0.70
    UnusedPrivate
    0.69
     photolibrary
    0.68
    Activations Density 1.972%

    No Known Activations