© 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. 161643
    Prev
    Next
    INDEX
    Explanations

    Arabic and English 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
    u
    1.22
    .
    1.05
    IVE
    0.95
    ной
    0.91
    ו
    0.89
    DA
    0.87
    gboost
    0.87
    SWITCH
    0.85
    CHE
    0.84
    PLAN
    0.84
    POSITIVE LOGITS
    :
    1.11
     NPCs
    1.10
     NYPD
    1.09
     UBND
    1.03
    <0x80>
    1.02
    ne
    1.02
     EUA
    0.99
     FYI
    0.98
     MTV
    0.93
    :&
    0.93
    Activations Density 0.000%

    No Known Activations