© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86346
    Prev
    Next
    INDEX
    Explanations

    step by step

    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_23_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
    fff
    0.40
    waveform
    0.38
    欅
    0.38
    FAIL
    0.37
    ineed
    0.36
     vine
    0.36
    λια
    0.36
    ><
    0.35
    db
    0.35
    دد
    0.35
    POSITIVE LOGITS
     present
    0.41
     ies
    0.39
     Citizens
    0.38
     obec
    0.38
     součas
    0.38
     exiting
    0.37
     curr
    0.36
     voluntarily
    0.36
     Grandma
    0.36
     polluting
    0.36
    Activations Density 0.000%

    No Known Activations