© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110057
    Prev
    Next
    INDEX
    Explanations

    gravelly voice

    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
    는
    1.33
    am
    1.22
     $
    1.20
    ie
    1.16
    1.16
    one
    1.13
    -
    1.09
    ى
    1.09
    是
    1.06
    ล
    1.06
    POSITIVE LOGITS
    t
    1.59
    tt
    1.52
     azienda
    1.41
    the
    1.37
     aident
    1.34
    υτό
    1.34
    ti
    1.34
     ingles
    1.34
    का
    1.31
     indiquer
    1.30
    Activations Density 0.000%

    No Known Activations