© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214358
    Prev
    Next
    INDEX
    Explanations

    David Hasselhoff

    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_16_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
    褴
    0.58
    CHI
    0.56
    K
    0.55
     Fighters
    0.53
     mantras
    0.53
    सीआर
    0.53
     orchards
    0.52
     CHI
    0.51
     arteries
    0.51
    Keb
    0.51
    POSITIVE LOGITS
    ة
    0.50
     samostat
    0.46
    слен
    0.46
     separar
    0.44
    ક્ત
    0.44
    seleccion
    0.43
     તરીકે
    0.43
    وزيع
    0.43
    individ
    0.42
    ,-\
    0.42
    Activations Density 0.000%

    No Known Activations