© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130887
    Prev
    Next
    INDEX
    Explanations

    Am followed by place or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    g
    1.34
    v
    1.34
    in
    1.23
    is
    1.16
    t
    1.14
    ان
    1.12
    L
    1.08
    on
    1.02
    い
    1.00
    ку
    0.97
    POSITIVE LOGITS
    ación
    0.89
     confronting
    0.79
    ética
    0.78
    én
    0.77
     свобод
    0.72
    és
    0.71
     walking
    0.71
    izações
    0.70
     devising
    0.70
    ší
    0.70
    Activations Density 0.002%

    No Known Activations