© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206799
    Prev
    Next
    INDEX
    Explanations

    запоминать, zap

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Effective
    0.41
     Effective
    0.39
     Gifford
    0.39
     —
    0.38
     efektif
    0.38
    ₱
    0.37
    salt
    0.37
    effective
    0.37
    湧
    0.36
    Ply
    0.36
    POSITIVE LOGITS
     замени
    0.41
     substitutes
    0.41
    aneo
    0.36
     renewables
    0.36
    addView
    0.36
     degli
    0.36
     kelamin
    0.36
    ạnh
    0.35
    aithe
    0.35
    enton
    0.35
    Activations Density 0.000%

    No Known Activations