© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205881
    Prev
    Next
    INDEX
    Explanations

    sorceress casting, priestess summoning

    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_6_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
    ،
    1.30
    ot
    1.14
    um
    1.14
    ut
    1.12
    、
    1.04
    </h2>
    0.98
    </h6>
    0.96
    ，“
    0.93
    ુ
    0.93
    ol
    0.90
    POSITIVE LOGITS
     is
    1.13
    д
    1.10
    ки
    1.07
     and
    0.96
     erano
    0.96
     would
    0.91
    т
    0.91
     were
    0.89
     on
    0.88
     ay
    0.88
    Activations Density 0.000%

    No Known Activations