© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153155
    Prev
    Next
    INDEX
    Explanations

    ai model responses

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    |
    0.51
    機会
    0.39
    incoming
    0.39
    interesse
    0.38
    |.
    0.37
     সহায়তা
    0.37
    estamp
    0.36
    |,
    0.35
    |"
    0.35
    Bright
    0.35
    POSITIVE LOGITS
    ⵜ
    0.43
     AREA
    0.40
     Area
    0.39
     Edited
    0.38
    ಾಯಿತು
    0.38
    ようになりました
    0.37
     goede
    0.36
     छोटा
    0.36
    },-
    0.36
     Authorized
    0.36
    Activations Density 0.013%

    No Known Activations