© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235504
    Prev
    Next
    INDEX
    Explanations

    Serengeti landscape

    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_46_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
     Instrum
    0.42
    屻
    0.42
     desafios
    0.42
    㕝
    0.41
     nhánh
    0.40
     проис
    0.40
    करों
    0.40
    city
    0.39
    branch
    0.39
     город
    0.39
    POSITIVE LOGITS
     خل
    0.39
    野生
    0.38
     Boardwalk
    0.37
    ኩ
    0.37
     boardwalk
    0.36
     Cal
    0.36
     cord
    0.35
    Cal
    0.35
    Cotton
    0.34
     seemed
    0.34
    Activations Density 0.000%

    No Known Activations