© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141995
    Prev
    Next
    INDEX
    Explanations

    JSON format for response

    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_12_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
    Из
    0.27
     MILLER
    0.25
    Ь
    0.24
    У
    0.24
     murder
    0.23
     verb
    0.23
    َ
    0.23
     discharged
    0.23
    Когда
    0.23
    и
    0.23
    POSITIVE LOGITS
    topia
    0.24
     ಥ
    0.23
    XPath
    0.22
    aop
    0.22
     透
    0.22
    šće
    0.21
     protegido
    0.21
     Nuevo
    0.21
     Nusa
    0.21
    Ftp
    0.21
    Activations Density 0.002%

    No Known Activations