© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90945
    Prev
    Next
    INDEX
    Explanations

    mother-in-law, ladybug

    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_3_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
     operandSize
    0.62
     arrhyth
    0.59
    )_{(
    0.59
     at
    0.59
    ༔
    0.59
     qubits
    0.58
     isoforms
    0.58
     administrativos
    0.58
     Евге
    0.57
     основы
    0.57
    POSITIVE LOGITS
    ة
    0.82
    า
    0.77
    ى
    0.77
    p
    0.73
    y
    0.65
    he
    0.64
    يد
    0.64
    ാ
    0.64
    ↵↵
    0.63
    ת
    0.60
    Activations Density 0.005%

    No Known Activations