© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7446
    Prev
    Next
    INDEX
    Explanations

    introduce or establish

    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_40_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
     பொறிய
    0.32
    டெ
    0.31
     பறி
    0.30
    AIRMAN
    0.30
    戤
    0.30
    ⤷
    0.30
    カタ
    0.29
    Slash
    0.29
    利
    0.29
    List
    0.29
    POSITIVE LOGITS
     follow
    0.63
    follow
    0.60
     segu
    0.54
     follows
    0.51
     følge
    0.51
     suivre
    0.50
     suivent
    0.47
    Follow
    0.47
    followers
    0.47
     Follow
    0.46
    Activations Density 0.039%

    No Known Activations