© 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. 141919
    Prev
    Next
    INDEX
    Explanations

    ham

    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
    டக்கலை
    0.38
     Preprint
    0.38
    elles
    0.37
    واں
    0.36
     elles
    0.36
     dominate
    0.36
     operazioni
    0.36
    徸
    0.36
     bông
    0.35
    াব্দ
    0.35
    POSITIVE LOGITS
    sterne
    0.41
    rising
    0.40
    tera
    0.40
    нен
    0.39
    gga
    0.39
    estial
    0.39
     ಪ್ಯಾ
    0.38
    ney
    0.38
    fantastic
    0.38
    ष्टी
    0.36
    Activations Density 0.001%

    No Known Activations