© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23356
    Prev
    Next
    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    стребо
    0.37
    ंक्शन
    0.34
     توسط
    0.34
     rufo
    0.32
    ᱸ
    0.32
    ยายน
    0.31
    ᆫ
    0.30
    摑
    0.30
    oram
    0.30
    alinga
    0.30
    POSITIVE LOGITS
    from
    2.75
     from
    2.69
     từ
    2.36
     FROM
    2.33
    จาก
    2.33
     från
    2.27
     From
    2.19
    从
    2.19
    From
    2.17
     dari
    2.14
    Activations Density 0.061%

    No Known Activations