© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48416
    Prev
    Next
    INDEX
    Explanations

    #!/bin scripts

    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_31_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
    Accessed
    0.46
    Dragged
    0.41
     calorimetric
    0.41
    DebuggerNonUser
    0.39
    aceted
    0.39
    Reusable
    0.39
    ဤ
    0.39
    ضو
    0.39
     orientated
    0.39
    Descriptors
    0.39
    POSITIVE LOGITS
     Edel
    0.41
     Think
    0.37
     inet
    0.37
     ECON
    0.36
     Nick
    0.36
     Glad
    0.36
     Vista
    0.36
     LAW
    0.36
     साध
    0.36
     Blade
    0.35
    Activations Density 0.001%

    No Known Activations