© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    programming code and certain formatting characters like brackets

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks/parentheses

    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
     A
    -0.61
     digital
    -0.57
     виправивши
    -0.57
     C
    -0.54
     D
    -0.54
    CURS
    -0.54
     B
    -0.52
    tvguidetime
    -0.52
    HEADERS
    -0.51
     H
    -0.51
    POSITIVE LOGITS
    Jax
    0.43
     précédents
    0.41
    +:+
    0.41
    +#+#
    0.41
    Eid
    0.40
    RTX
    0.40
    Nio
    0.39
     avrebbe
    0.39
    Kia
    0.38
    Oz
    0.38
    Activations Density 7.387%

    No Known Activations