© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259574
    Prev
    Next
    INDEX
    Explanations

    exception and error handling

    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_22_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
    3
    0.41
    Realistic
    0.41
    Ex
    0.40
    9
    0.38
    ോ
    0.38
    Pastor
    0.38
    Busy
    0.38
     Eas
    0.38
    5
    0.37
     realistic
    0.37
    POSITIVE LOGITS
     duel
    0.46
    Ꮰ
    0.42
     अंतर
    0.41
    င့်
    0.41
     ዋ
    0.41
     beats
    0.40
    मेन
    0.40
     buyers
    0.40
     घटना
    0.40
     collusion
    0.39
    Activations Density 0.000%

    No Known Activations