© 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. 166567
    Prev
    Next
    INDEX
    Explanations

    specifying replacements or alternatives

    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
    noindent
    0.36
    عين
    0.34
    নারায়ণ
    0.33
     नजर
    0.32
    ग्राहक
    0.32
     주민
    0.32
    গরে
    0.32
    <unused35>
    0.32
    étera
    0.32
    Punjab
    0.32
    POSITIVE LOGITS
     odlu
    0.39
     amaz
    0.37
     Arithmetic
    0.35
     צ
    0.34
     Auto
    0.34
     exempt
    0.34
     καλ
    0.34
     arithmetic
    0.34
     musi
    0.33
    jeno
    0.33
    Activations Density 0.088%

    No Known Activations