© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110686
    Prev
    Next
    INDEX
    Explanations

    foreign language punctuation

    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
     (
    1.16
    h
    1.01
     gode
    0.99
    ্ড
    0.94
    ೇ
    0.93
    িব
    0.88
    ard
    0.86
     zacz
    0.86
     pares
    0.86
     сдела
    0.85
    POSITIVE LOGITS
     that
    1.49
    ،
    1.37
    、
    1.34
    ă
    1.21
    ),
    1.20
    ン
    1.16
    ज
    1.14
     was
    1.11
    }$,
    1.11
    ，
    1.11
    Activations Density 0.000%

    No Known Activations