© 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. 38558
    Prev
    Next
    INDEX
    Explanations

    beware, beseech, verily, doth

    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
    I
    0.81
    Was
    0.63
    (
    0.63
    Tarea
    0.63
    Valid
    0.62
    Lesson
    0.62
    Bet
    0.60
    Need
    0.60
    Tek
    0.60
    Bes
    0.59
    POSITIVE LOGITS
    ре
    0.71
    ру
    0.71
    ？）
    0.68
    ти
    0.64
     grosseur
    0.63
     posicion
    0.62
    ુ
    0.62
     pintar
    0.61
    ан
    0.60
    ра
    0.60
    Activations Density 0.000%

    No Known Activations