© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49444
    Prev
    Next
    INDEX
    Explanations

    android manifest or parameters

    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
    </i>
    0.63
    تر
    0.63
    死亡
    0.62
    كين
    0.62
    嗓
    0.61
    in
    0.59
    también
    0.59
     and
    0.59
    我們
    0.59
    También
    0.59
    POSITIVE LOGITS
    <0xBF>
    0.74
     porosity
    0.69
     ὁ
    0.69
     semigroup
    0.69
     torsional
    0.66
     removable
    0.65
    poque
    0.64
     slid
    0.64
     periodicity
    0.63
     resonators
    0.63
    Activations Density 0.000%

    No Known Activations