© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212820
    Prev
    Next
    INDEX
    Explanations

    friend, followed by description or action

    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_5_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
    ?
    1.14
    '
    1.08
    !
    1.08
     it
    1.01
    中
    1.00
    ना
    0.98
    in
    0.97
    ו
    0.97
    有
    0.95
    on
    0.92
    POSITIVE LOGITS
    z
    1.55
    ский
    1.47
    ک
    1.40
    x
    1.38
    м
    1.34
    v
    1.29
    вання
    1.19
    อง
    1.17
    g
    1.16
    тся
    1.16
    Activations Density 0.005%

    No Known Activations