© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35392
    Prev
    Next
    INDEX
    Explanations

    landmarked organizing acts

    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_11_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
    0.43
    ese
    0.39
     skate
    0.38
     c
    0.37
     when
    0.37
    rir
    0.36
    $
    0.36
    g
    0.36
     Heritage
    0.36
     roar
    0.35
    POSITIVE LOGITS
    FormProvider
    0.40
    opencamera
    0.40
    вок
    0.39
     включая
    0.38
     उपायों
    0.38
    Cursors
    0.37
     innov
    0.37
    كمال
    0.36
     опубликован
    0.36
    деся
    0.36
    Activations Density 0.050%

    No Known Activations