© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143142
    Prev
    Next
    INDEX
    Explanations

    excavations, extinguish, ocultar

    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_0_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
    го
    1.63
    र
    1.55
    S
    1.52
    L
    1.44
     a
    1.41
    O
    1.34
    อ
    1.31
    E
    1.30
    1.28
    ৩
    1.19
    POSITIVE LOGITS
    ت
    2.58
    t
    1.79
    تج
    1.60
    تس
    1.52
    tar
    1.49
    todos
    1.49
    s
    1.48
    tu
    1.45
    tions
    1.45
    h
    1.45
    Activations Density 0.000%

    No Known Activations