© 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. 32312
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

    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
    固体
    0.41
     indig
    0.40
     വിവ
    0.40
    FDMA
    0.40
     Inert
    0.39
     Degree
    0.38
     isti
    0.38
    晹
    0.38
     informa
    0.38
     hous
    0.38
    POSITIVE LOGITS
    ("<
    0.43
    ales
    0.41
     uploading
    0.36
    @
    0.36
    ["
    0.35
    ('['
    0.35
    施設の
    0.34
    @[+][
    0.34
    χν
    0.34
     αρχ
    0.34
    Activations Density 0.002%

    No Known Activations