© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134452
    Prev
    Next
    INDEX
    Explanations

    giving back to community

    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_37_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
     संसदीय
    0.42
    ’;
    0.40
    arduino
    0.40
     বাস্তবিক
    0.37
    ’:
    0.37
     গতি
    0.36
     Arduino
    0.36
    ٹوں
    0.35
    델
    0.35
     स्पीड
    0.35
    POSITIVE LOGITS
    back
    0.43
     back
    0.42
     tilbake
    0.42
     giving
    0.38
     perd
    0.38
    Back
    0.37
     contributions
    0.37
     tillbaka
    0.37
     Back
    0.36
    Giving
    0.36
    Activations Density 0.000%

    No Known Activations