© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229715
    Prev
    Next
    INDEX
    Explanations

    ver + common German verb endings

    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_6_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
    상
    1.23
    %)
    0.96
    ご
    0.95
    때
    0.94
    ER
    0.94
    在我
    0.93
     haría
    0.89
    승
    0.89
    ک
    0.89
    ق
    0.88
    POSITIVE LOGITS
    er
    1.38
    h
    1.31
    el
    1.27
    t
    1.23
    o
    1.19
    ar
    1.17
    aa
    1.17
    in
    1.16
    a
    1.15
    ac
    1.10
    Activations Density 0.000%

    No Known Activations