© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90680
    Prev
    Next
    INDEX
    Explanations

    knight, tournament, riders

    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_3_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
     can
    0.86
    ש
    0.69
     cradle
    0.66
     are
    0.65
     televisión
    0.63
     recorr
    0.62
     PERSON
    0.62
     человека
    0.59
     was
    0.59
     ব্যক্তিদের
    0.59
    POSITIVE LOGITS
    ES
    0.68
    ጠት
    0.66
    ם
    0.64
    AT
    0.64
    ات
    0.62
    ב
    0.62
    atok
    0.61
     obej
    0.61
    ουν
    0.61
    y
    0.61
    Activations Density 0.000%

    No Known Activations