© 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. 58609
    Prev
    Next
    INDEX
    Explanations

    silicon, brazilian,mineral

    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
    t
    1.38
    1.33
    j
    1.30
    ER
    1.27
    f
    1.23
    IC
    1.18
    a
    1.16
     and
    1.15
    c
    1.09
    b
    1.05
    POSITIVE LOGITS
    in
    1.04
     γεγον
    0.92
     SoaException
    0.91
    有害
    0.90
    お届け
    0.89
    おしゃれ
    0.88
    有序
    0.88
     infliction
    0.85
    க்கும்
    0.85
    お手
    0.84
    Activations Density 0.042%

    No Known Activations