© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    alphanumeric IDs, codes, names and other metadata from code-related documents

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    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
    findpost
    -0.57
    긍
    -0.41
    <%@
    -0.40
    ImageContext
    -0.40
    ampa
    -0.38
     Virgin
    -0.38
    pbs
    -0.38
    í
    -0.37
    k
    -0.37
    og
    -0.37
    POSITIVE LOGITS
     externi
    0.76
    4
    0.76
    5
    0.76
    7
    0.75
    6
    0.75
    3
    0.71
    LookAnd
    0.69
    8
    0.68
    9
    0.63
    ❹
    0.62
    Activations Density 11.038%

    No Known Activations