© 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-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91281
    Prev
    Next
    INDEX
    Explanations

    say Please

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Am
    0.45
     Nhân
    0.42
     It
    0.41
     Love
    0.41
     Leslie
    0.40
    al
    0.40
     Κα
    0.39
    [
    0.39
     Aut
    0.39
     Hope
    0.39
    POSITIVE LOGITS
    Young
    0.50
    Domestic
    0.45
    subj
    0.42
    Former
    0.41
     jungen
    0.40
    Subjects
    0.40
    mermaid
    0.40
    Turns
    0.40
    Working
    0.39
    bouncer
    0.39
    Activations Density 0.008%

    No Known Activations