© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17805
    Prev
    Next
    INDEX
    Explanations

    returning to normal activities

    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_34_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
     securing
    0.41
    jell
    0.39
    똥
    0.38
    Dre
    0.38
     Zuh
    0.37
    xaxis
    0.37
    erdings
    0.37
     Uno
    0.36
    ෞ
    0.36
    ስተ
    0.36
    POSITIVE LOGITS
     return
    1.34
     возвра
    1.26
    return
    1.14
     RETURN
    1.13
     вернуться
    1.12
    返回
    1.10
    กลับ
    1.10
    に戻
    1.10
    Return
    1.09
     верну
    1.09
    Activations Density 0.036%

    No Known Activations