© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137272
    Prev
    Next
    INDEX
    Explanations

    changing wording

    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_12_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
    ي
    0.59
    ين
    0.50
     demikian
    0.50
    ان
    0.49
    い
    0.49
    ный
    0.48
    ные
    0.48
     seperti
    0.46
    મ
    0.46
     carts
    0.46
    POSITIVE LOGITS
    cn
    0.56
    CPM
    0.52
    rams
    0.52
    cd
    0.51
    lç
    0.51
    t
    0.50
    pp
    0.50
    cH
    0.49
    itä
    0.48
    v
    0.48
    Activations Density 0.014%

    No Known Activations