© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136783
    Prev
    Next
    INDEX
    Explanations

    Object.assign, Object.keys, Object.entries

    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_12_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
     Focusing
    0.57
     namun
    0.54
    ral
    0.53
    eres
    0.50
    ٨
    0.50
    asi
    0.50
    ano
    0.50
    酶
    0.49
    礽
    0.48
    nde
    0.47
    POSITIVE LOGITS
    s
    0.64
    texttt
    0.58
     McGu
    0.57
    θέ
    0.56
     médico
    0.55
     ortho
    0.55
     additional
    0.55
     счита
    0.55
     Médico
    0.54
     tér
    0.52
    Activations Density 0.000%

    No Known Activations