© 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. 103424
    Prev
    Next
    INDEX
    Explanations

    impermancent

    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
    a
    1.61
    en
    1.36
    el
    1.25
    x
    1.24
     (
    1.23
    0
    1.23
    e
    1.23
    i
    1.21
    ed
    1.16
    as
    1.15
    POSITIVE LOGITS
    ید
    1.12
    نی
    1.09
    نے
    0.98
    .
    0.94
    ний
    0.90
    িয়ে
    0.86
    ित्र
    0.84
    ಬ್ಬಿಣ
    0.84
    یر
    0.83
    ने
    0.82
    Activations Density 0.000%

    No Known Activations