© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107950
    Prev
    Next
    INDEX
    Explanations

    Windows

    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_1_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
    স
    1.12
    at
    1.10
    ى
    1.08
     for
    1.07
    4
    1.05
    ک
    1.05
    و
    1.05
    ת
    1.04
    ق
    1.03
    and
    1.02
    POSITIVE LOGITS
    하고
    0.89
    man
    0.89
    henium
    0.87
    t
    0.87
     luglio
    0.86
    gunakan
    0.86
    arma
    0.84
    hesion
    0.84
    ovanie
    0.83
    Width
    0.82
    Activations Density 0.005%

    No Known Activations