© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154126
    Prev
    Next
    INDEX
    Explanations

    inheritance and hierarchy

    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_23_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
     ధ
    0.43
    myLabels
    0.43
     مشتمل
    0.42
    학
    0.40
    genomes
    0.40
    iritual
    0.39
    itorios
    0.39
    Сма
    0.39
    beste
    0.38
     cultivo
    0.37
    POSITIVE LOGITS
     Forced
    0.46
     forced
    0.45
     prvo
    0.43
     ነገር
    0.40
     expended
    0.39
     peculiarity
    0.38
     ऐसा
    0.38
     Conte
    0.37
     薄
    0.37
     Heidi
    0.37
    Activations Density 0.000%

    No Known Activations