© 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. 13584
    Prev
    Next
    INDEX
    Explanations

    financial aid and quarters

    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
     verità
    0.53
     Вай
    0.52
    ை
    0.52
    ა
    0.52
     ausreiche
    0.51
     FormData
    0.49
     Wahrheit
    0.48
     اعلی
    0.48
    ਾ
    0.48
    يئة
    0.48
    POSITIVE LOGITS
    Eric
    0.50
    ظل
    0.50
     &
    0.49
    ́ch
    0.49
    appar
    0.48
    жни
    0.46
    closure
    0.46
    }$.,
    0.46
     डायरे
    0.46
    lichess
    0.45
    Activations Density 0.014%

    No Known Activations