© 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. 135215
    Prev
    Next
    INDEX
    Explanations

    League schools

    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
    UR
    1.05
    ﾁ
    0.93
    सी
    0.89
     hypotheses
    0.89
     figurine
    0.89
    یی
    0.89
    LE
    0.88
     to
    0.88
     diffusion
    0.88
     quantifier
    0.87
    POSITIVE LOGITS
    ти
    1.02
    with
    0.98
    ди
    0.96
    ुअल
    0.92
     Wahr
    0.90
     Beginn
    0.88
    $).
    0.86
    }|^
    0.86
    lefthar
    0.86
    devDependencies
    0.84
    Activations Density 0.000%

    No Known Activations