© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237386
    Prev
    Next
    INDEX
    Explanations

    plural possessive or contraction separator

    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_25_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
    any
    0.42
    கால
    0.41
    ñ
    0.40
    week
    0.40
     современной
    0.40
    imh
    0.39
    ún
    0.38
    ŋ
    0.38
    quay
    0.38
    plane
    0.37
    POSITIVE LOGITS
     jednotliv
    0.40
     vreau
    0.39
     ebben
    0.38
     entire
    0.38
     slander
    0.38
     assolutamente
    0.37
     aggression
    0.37
    したい
    0.36
     repack
    0.36
    们的
    0.36
    Activations Density 0.001%

    No Known Activations