© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144363
    Prev
    Next
    INDEX
    Explanations

    analyse followed by context

    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_0_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
    İ
    1.28
    st
    1.21
    Y
    1.20
    Ě
    1.16
    ン
    1.15
    Ğ
    1.11
    ن
    1.09
    ।'
    1.06
    '
    1.05
     RECOMMEND
    1.05
    POSITIVE LOGITS
    ни
    2.09
    et
    1.80
    но
    1.79
    u
    1.76
    на
    1.68
    at
    1.65
    다
    1.63
    o
    1.47
    e
    1.46
    ა
    1.41
    Activations Density 0.000%

    No Known Activations