© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181926
    Prev
    Next
    INDEX
    Explanations

    accessible to everyone

    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_29_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
    变
    0.40
     xạ
    0.39
     đối
    0.39
     deceived
    0.39
     abused
    0.38
     meat
    0.38
     burned
    0.38
    သော
    0.37
     quals
    0.37
     开发
    0.36
    POSITIVE LOGITS
    náv
    0.45
    esthetics
    0.43
    Ⅼ
    0.42
    Ș
    0.41
     внима
    0.41
    šem
    0.41
    glyphicon
    0.40
    𝚓
    0.39
     peasantry
    0.39
    Keep
    0.39
    Activations Density 0.003%

    No Known Activations