© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138070
    Prev
    Next
    INDEX
    Explanations

    mental discipline

    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
    <unused49>
    0.54
     plaintiffs
    0.54
     énfasis
    0.52
     YEAR
    0.52
     идея
    0.50
     spots
    0.50
     residents
    0.49
     screws
    0.49
     हार्
    0.49
    uetooth
    0.48
    POSITIVE LOGITS
    Ed
    0.67
    Z
    0.65
    Does
    0.61
    Is
    0.56
    Has
    0.54
    Did
    0.53
    Mul
    0.53
    Yesterday
    0.53
    폭
    0.53
    Ah
    0.52
    Activations Density 0.005%

    No Known Activations