© 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. 9195
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    oai_token-act-pair · gemini-2.0-flash

    say "per"

    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
     per
    -1.91
     Per
    -1.62
    Per
    -1.61
    per
    -1.58
    PER
    -1.25
     PER
    -1.18
    perPage
    -0.69
    PerPage
    -0.68
     percent
    -0.65
    perc
    -0.63
    POSITIVE LOGITS
     approval
    1.75
     Approval
    1.69
     approved
    1.57
    Approval
    1.50
     Approved
    1.49
     approvals
    1.49
     approve
    1.48
     approving
    1.47
    Approved
    1.45
     Approve
    1.43
    Activations Density 3.666%

    No Known Activations