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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7145
    Prev
    Next
    INDEX
    Explanations

    strings within code and text that denote different types of separation

    oai_token-act-pair · gemini-2.0-flash

    Formal texts

    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
    in
    -1.02
    a
    -1.02
    d
    -1.01
    v
    -1.01
    as
    -1.00
    y
    -1.00
    n
    -0.98
    h
    -0.95
    at
    -0.95
    e
    -0.94
    POSITIVE LOGITS
    iffance
    0.70
    adeloupe
    0.70
    akaian
    0.68
    unicip
    0.67
    abello
    0.67
     Anſ
    0.67
    ipheral
    0.66
    ratulations
    0.66
     uſe
    0.65
    lynol
    0.65
    Activations Density 1.798%

    No Known Activations