© 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. 143267
    Prev
    Next
    INDEX
    Explanations

    tackling

    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
    ం
    1.50
    ס
    1.16
     불구하고
    1.09
    elijke
    1.06
    schutz
    1.05
    افظ
    1.05
    в
    1.03
    с
    1.02
    c
    0.99
    ต้อง
    0.98
    POSITIVE LOGITS
    ll
    1.79
    u
    1.50
    ing
    1.49
    ام
    1.47
    í
    1.45
    ne
    1.44
    li
    1.43
    ل
    1.42
    드
    1.36
    r
    1.35
    Activations Density 0.000%

    No Known Activations