© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9600
    Prev
    Next
    INDEX
    Explanations

    phone and operator

    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_13_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
     -
    0.61
    ie
    0.60
     Navy
    0.50
     g
    0.49
     Army
    0.49
     i
    0.49
     for
    0.48
    light
    0.48
    ig
    0.48
    <0x0D>
    0.47
    POSITIVE LOGITS
    کا
    0.53
    レベル
    0.52
    ベル
    0.51
     infección
    0.51
    کل
    0.51
    ESSAGE
    0.50
    जा
    0.50
    صب
    0.49
    ErrorCode
    0.49
    アジア
    0.49
    Activations Density 0.030%

    No Known Activations