© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13586
    Prev
    Next
    INDEX
    Explanations

    killer features or serial killer

    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_13_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
    皑
    0.17
     уда
    0.16
     đặc
    0.16
     Leibniz
    0.16
     chmod
    0.16
    あら
    0.15
    ี้ย
    0.15
    焓
    0.15
    ొ
    0.15
     inscri
    0.15
    POSITIVE LOGITS
    INE
    0.17
    <div>
    0.17
    ts
    0.17
    An
    0.16
    NEW
    0.16
    requent
    0.16
    ர்கள்
    0.16
    are
    0.16
    1
    0.16
    Who
    0.16
    Activations Density 0.002%

    No Known Activations