© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22885
    Prev
    Next
    INDEX
    Explanations

    siblings

    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_56_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
    ेंटिस
    0.38
    ologischen
    0.37
    ᱪ
    0.37
    orsement
    0.36
    ennzeichnet
    0.36
    HasStarred
    0.36
    ಧಾರ
    0.36
    ীনে
    0.35
    ത്തര
    0.35
    ေသ
    0.35
    POSITIVE LOGITS
     brothers
    0.69
     sisters
    0.56
    brothers
    0.54
     Brothers
    0.52
    兄弟
    0.49
     frères
    0.48
    ,%
    0.46
    ,_
    0.45
     kardeş
    0.44
     besuchte
    0.44
    Activations Density 0.010%

    No Known Activations