© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111600
    Prev
    Next
    INDEX
    Explanations

    но ако

    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_2_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
    л
    1.67
    ל
    1.38
    ل
    1.27
     or
    1.23
    ल
    1.16
    تر
    1.14
    का
    1.13
    ک
    1.07
    나
    1.01
    리
    1.00
    POSITIVE LOGITS
    ер
    1.10
    া
    1.06
    a
    1.05
    </h3>
    1.04
    ați
    1.02
     دين
    0.95
    هي
    0.94
     problème
    0.92
     matériel
    0.90
    ياء
    0.89
    Activations Density 0.000%

    No Known Activations