© 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
    2. Gemma-3-27B-IT
    3. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 35147
    Prev
    Next
    INDEX
    Explanations

    avenge / avenging

    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_7_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
     grandiose
    1.00
     వైసీపీ
    0.93
    น
    0.93
    नपुर
    0.91
    н
    0.91
     குறித்து
    0.90
     bolster
    0.89
    čkom
    0.89
     SimSun
    0.87
     notepad
    0.86
    POSITIVE LOGITS
     of
    1.38
    ates
    1.20
    3
    1.14
    ों
    1.13
    1
    1.07
    í
    1.00
    );
    0.98
    9
    0.98
    ات
    0.97
    den
    0.96
    Activations Density 0.001%

    No Known Activations