© 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. 112854
    Prev
    Next
    INDEX
    Explanations

    dw followed by specific suffixes

    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
    ס
    1.61
    ре
    1.55
    า
    1.52
    ا
    1.41
    ри
    1.40
    س
    1.39
    ת
    1.39
    a
    1.24
    ل
    1.24
    ल
    1.23
    POSITIVE LOGITS
    ada
    1.13
    ,
    1.13
    IS
    1.13
    EST
    1.10
    IN
    1.08
    ão
    1.05
     underestimates
    1.04
    AN
    1.03
    ER
    1.02
    ﻳ
    1.00
    Activations Density 0.000%

    No Known Activations