© 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. 206351
    Prev
    Next
    INDEX
    Explanations

    product versions

    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
     twelfth
    0.47
     PWM
    0.44
    )';
    0.41
     Sitt
    0.40
     zero
    0.39
     PAM
    0.38
    zero
    0.38
    されており
    0.38
     tenth
    0.38
     №
    0.38
    POSITIVE LOGITS
     دینے
    0.41
     generazione
    0.40
     ген
    0.39
    Containing
    0.38
    伝説
    0.37
     генера
    0.37
    нений
    0.36
     ঘা
    0.36
    راهيم
    0.36
     آزمایش
    0.36
    Activations Density 0.000%

    No Known Activations