© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67120
    Prev
    Next
    INDEX
    Explanations

    psychology

    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_46_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
    𝚆
    0.41
    隗
    0.39
    Brow
    0.39
    umet
    0.38
     ++;
    0.38
     پال
    0.38
    Cameron
    0.38
     مرک
    0.38
    以來
    0.37
     tuner
    0.37
    POSITIVE LOGITS
     தர
    0.41
     `#
    0.41
     psychology
    0.38
     образу
    0.38
    psy
    0.38
    Psy
    0.37
     psychologists
    0.37
    ＃
    0.37
     (#
    0.36
     Psychology
    0.36
    Activations Density 0.001%

    No Known Activations