© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175660
    Prev
    Next
    INDEX
    Explanations

    hiring or recruitment

    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_24_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
     шля
    0.38
     अक
    0.38
     অবস্থা
    0.36
    謎
    0.36
     आशंका
    0.36
     تهیه
    0.36
    шты
    0.35
    Around
    0.34
     रैंकिंग
    0.33
    M
    0.33
    POSITIVE LOGITS
    ⏟
    0.41
     deductive
    0.39
     newToken
    0.37
    ractive
    0.35
     debtor
    0.35
     artes
    0.35
     জগতে
    0.35
     concluded
    0.35
    ျေး
    0.34
    spruch
    0.34
    Activations Density 0.001%

    No Known Activations