© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195116
    Prev
    Next
    INDEX
    Explanations

    red herrings

    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_15_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
     техни
    0.50
     torpedo
    0.46
    ่า
    0.46
    凶
    0.46
     клиен
    0.44
     требо
    0.43
    ady
    0.42
     technical
    0.42
     fren
    0.42
    鸡
    0.41
    POSITIVE LOGITS
    HLER
    0.51
    GER
    0.50
     Latinos
    0.50
    PARA
    0.49
    WELL
    0.48
     बीएसटीसी
    0.48
     Zeits
    0.47
    SANIT
    0.47
    睉
    0.47
    ститут
    0.47
    Activations Density 0.000%

    No Known Activations