© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9283
    Prev
    Next
    INDEX
    Explanations

    mischief, trouble, or rebellion

    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
    "}
    0.47
    }
    0.46
    ковое
    0.45
    ICO
    0.44
     waterproofing
    0.42
    泛
    0.42
    })
    0.42
    pop
    0.41
     ЕГЭ
    0.41
    Pop
    0.41
    POSITIVE LOGITS
    h
    0.64
     digitar
    0.52
     Lili
    0.50
     বিঘ
    0.49
    เล
    0.49
     dirs
    0.46
     привле
    0.46
    ilha
    0.45
     dared
    0.45
    २
    0.45
    Activations Density 0.120%

    No Known Activations