© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54005
    Prev
    Next
    INDEX
    Explanations

    names and sports

    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_55_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
     Marco
    0.44
     Agustín
    0.44
     Sebastián
    0.43
     Mumbai
    0.42
     '_
    0.42
     direita
    0.40
     Lehenga
    0.39
     Jessica
    0.39
     Auckland
    0.39
     Víctor
    0.38
    POSITIVE LOGITS
    েম
    0.42
    ᐉ
    0.42
     proving
    0.41
     спорт
    0.38
    สวัสดี
    0.37
     hematopoietic
    0.37
     sporty
    0.36
    ManyToManyField
    0.36
     psychiatric
    0.36
    trone
    0.36
    Activations Density 0.001%

    No Known Activations