© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106088
    Prev
    Next
    INDEX
    Explanations

    CH followed by specific suffixes

    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_1_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
     cataly
    1.30
    ة
    1.29
     alebo
    1.16
     a
    1.13
     that
    1.08
    으로
    1.02
     of
    1.01
     revital
    0.98
     que
    0.98
     و
    0.97
    POSITIVE LOGITS
    f
    1.66
    re
    1.56
    v
    1.43
    و
    1.35
    n
    1.34
    an
    1.27
    the
    1.27
    ί
    1.23
    on
    1.20
    ts
    1.20
    Activations Density 0.001%

    No Known Activations