© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225147
    Prev
    Next
    INDEX
    Explanations

    **VCS, VC, VE acronyms**

    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_10_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
    値
    0.81
    OUR
    0.80
    рядок
    0.76
    வதி
    0.75
    ות
    0.73
     Может
    0.73
    )
    0.73
    Osaka
    0.72
    ),
    0.72
    irthday
    0.72
    POSITIVE LOGITS
    ib
    0.84
    0.75
    '
    0.71
    。
    0.70
    y
    0.70
     VO
    0.69
     is
    0.68
    <0x99>
    0.67
    甚至
    0.67
    am
    0.66
    Activations Density 0.004%

    No Known Activations