© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201906
    Prev
    Next
    INDEX
    Explanations

    idealism, idealista

    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_6_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
     a
    1.09
    א
    1.07
    ری
    1.05
    מ
    1.02
    م
    0.99
     albo
    0.96
    ח
    0.95
     on
    0.93
    a
    0.91
     odak
    0.91
    POSITIVE LOGITS
    ，
    1.03
    బ్ద
    0.85
    ،
    0.81
    ídu
    0.79
    ícia
    0.78
    。
    0.76
    ూ
    0.76
    of
    0.74
    "
    0.74
    ，「
    0.74
    Activations Density 0.000%

    No Known Activations