© 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. 227448
    Prev
    Next
    INDEX
    Explanations

    KSA, Jey Uso, fruit

    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
    ี
    1.23
    ત
    1.22
    İ
    1.16
    я
    1.13
    ι
    1.13
    স
    1.10
    Ở
    1.10
    دي
    1.09
    س
    1.09
    اس
    1.09
    POSITIVE LOGITS
     మాత్రమే
    0.99
    ul
    0.93
    ut
    0.91
     ].
    0.89
    to
    0.86
     NSTX
    0.85
    ndrome
    0.85
     JSON
    0.84
    னர்
    0.83
     อาจ
    0.83
    Activations Density 0.000%

    No Known Activations