© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139677
    Prev
    Next
    INDEX
    Explanations

    bypassing techniques

    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_12_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
     lumped
    0.46
    ೆಯಿಂದ
    0.45
     neglects
    0.43
     ਨ
    0.42
     meaningless
    0.42
    ্যানের
    0.41
     bypass
    0.40
     vielleicht
    0.40
     ಎರಡು
    0.40
    ܡ
    0.40
    POSITIVE LOGITS
    t
    0.46
    4
    0.43
    _
    0.42
    v
    0.41
    $
    0.40
    Loading
    0.39
    6
    0.39
    1
    0.39
    Ö
    0.38
    Ult
    0.38
    Activations Density 0.003%

    No Known Activations