© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42520
    Prev
    Next
    INDEX
    Explanations

    simple example

    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_22_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
    渫
    0.36
    राबाद
    0.35
    礼
    0.35
    ্যার
    0.34
     चौरा
    0.34
     tacked
    0.34
    uters
    0.33
    ﮕ
    0.33
    aksan
    0.33
    Accessible
    0.33
    POSITIVE LOGITS
     instrumento
    0.35
    ǿ
    0.35
     yaitu
    0.34
     volto
    0.34
     strain
    0.34
     evidences
    0.34
     fase
    0.33
    выя
    0.33
    oxia
    0.33
     nanoparticles
    0.33
    Activations Density 0.020%

    No Known Activations