© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248849
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Public
    1.98
    Public
    1.72
     公
    1.02
    公
    0.96
     PUBLIC
    0.93
     Private
    0.86
     पब्लिक
    0.82
     Pública
    0.79
     Pub
    0.78
     পাবলিক
    0.76
    POSITIVE LOGITS
    闂
    0.40
    Dependency
    0.36
    然
    0.36
    RuntimeException
    0.35
    吧
    0.34
    қда
    0.33
     있는데
    0.33
    Penis
    0.33
    Preference
    0.33
     densément
    0.33
    Activations Density 0.031%

    No Known Activations