© 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. 161756
    Prev
    Next
    INDEX
    Explanations

    speed limits and warnings

    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
    ီ
    0.46
    仪表
    0.41
     young
    0.39
     شباب
    0.38
     твор
    0.37
    batim
    0.37
     ਗਿਆ
    0.37
    䍧
    0.37
     jovem
    0.37
     الحم
    0.37
    POSITIVE LOGITS
     psal
    0.37
    辜
    0.37
     ár
    0.36
    ilet
    0.36
     org
    0.36
    మం
    0.35
    '>";
    0.35
     Egal
    0.34
    Addition
    0.34
     Org
    0.34
    Activations Density 0.011%

    No Known Activations