© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12770
    Prev
    Next
    INDEX
    Explanations

    inverse functions and matrices

    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_13_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
    த்தில்
    0.38
     C
    0.35
    вих
    0.33
    is
    0.32
    ított
    0.32
    ક્ત
    0.31
    ह्
    0.30
     durchgeführt
    0.30
     blisters
    0.30
     պ
    0.30
    POSITIVE LOGITS
    3
    0.35
     doubling
    0.34
    string
    0.33
     overshadow
    0.32
         
    0.31
    e
    0.30
    taking
    0.30
     пря
    0.29
     prendere
    0.29
     निकालना
    0.29
    Activations Density 0.003%

    No Known Activations