© 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. 18552
    Prev
    Next
    INDEX
    Explanations

    ax^2 + bx + c = 0

    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
    sqrt
    0.53
     sqrt
    0.46
    √
    0.44
    √(
    0.42
    msqrt
    0.41
    }[(
    0.39
    RACT
    0.36
    [(\
    0.35
     √
    0.35
    square
    0.34
    POSITIVE LOGITS
    coefficients
    0.46
     equations
    0.43
     समीकरण
    0.43
     coefficients
    0.42
     equation
    0.41
     coefficient
    0.41
    Equation
    0.41
     Coefficients
    0.41
    rocery
    0.40
     ecuación
    0.39
    Activations Density 0.008%

    No Known Activations