© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44211
    Prev
    Next
    INDEX
    Explanations

    way back

    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_13_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
    et
    0.64
    e
    0.59
    am
    0.59
    museum
    0.58
    hift
    0.58
     museum
    0.57
     संग्रहालय
    0.57
    hwar
    0.57
     现在
    0.57
    h
    0.54
    POSITIVE LOGITS
    </i>
    0.61
    κο
    0.61
    ="+
    0.53
    ای
    0.52
    ლი
    0.52
     από
    0.51
     éc
    0.51
    ﺳ
    0.50
    лі
    0.50
     élast
    0.50
    Activations Density 0.000%

    No Known Activations