© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242555
    Prev
    Next
    INDEX
    Explanations

    rgba color values

    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_40_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
     zeroes
    0.52
     metres
    0.43
     zero
    0.42
     órdenes
    0.42
     zeros
    0.41
     guesses
    0.39
    ゼロ
    0.38
    零
    0.38
     století
    0.37
     трансформа
    0.37
    POSITIVE LOGITS
     LLC
    0.41
    getCharAt
    0.41
    ៗ
    0.39
    பை
    0.37
    strated
    0.36
     Wear
    0.36
     पहनने
    0.36
    着
    0.36
    ﻯ
    0.35
    IZE
    0.35
    Activations Density 0.001%

    No Known Activations