© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36501
    Prev
    Next
    INDEX
    Explanations

    "Power" followed by quotation marks

    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_31_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
    दिष्ट
    0.33
     obe
    0.31
     देऊन
    0.31
     घेऊन
    0.30
     conso
    0.29
    茼
    0.29
     வைத்து
    0.28
     자신의
    0.28
    ラム
    0.27
     eccentric
    0.27
    POSITIVE LOGITS
     issn
    0.34
     }
    0.32
     ISSN
    0.30
    '}
    0.30
    ǯ
    0.30
    "}
    0.29
    ಳು
    0.29
    };
    0.29
    "}}
    0.29
    гре
    0.28
    Activations Density 0.081%

    No Known Activations