© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13248
    Prev
    Next
    INDEX
    Explanations

    drowning and staying afloat

    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
    ной
    0.51
    ных
    0.47
     ч
    0.43
    ဃ
    0.43
     ganz
    0.42
    чных
    0.40
     –
    0.39
     receptor
    0.39
     migrations
    0.39
     Ely
    0.38
    POSITIVE LOGITS
    溺
    0.52
    浮
    0.49
    あるいは
    0.49
    roir
    0.48
     drowned
    0.48
    水
    0.47
    %。
    0.47
     drown
    0.46
    ک
    0.46
    swim
    0.45
    Activations Density 0.026%

    No Known Activations