© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151336
    Prev
    Next
    INDEX
    Explanations

    math equations

    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_60_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
     POC
    0.48
     Ν
    0.48
    -(
    0.43
     Раз
    0.43
     Ρ
    0.43
     وأ
    0.43
     Ս
    0.43
     아
    0.43
    $.
    0.42
     Ç
    0.42
    POSITIVE LOGITS
    '};
    0.45
    ູ
    0.43
     scanty
    0.43
    /';
    0.41
    โปร
    0.40
    ();}
    0.40
    ബി
    0.38
     محسوس
    0.38
    開心
    0.38
     reproach
    0.38
    Activations Density 0.005%

    No Known Activations