© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170552
    Prev
    Next
    INDEX
    Explanations

    are

    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_56_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
     far
    0.46
     שלה
    0.42
     whist
    0.41
     değişiklik
    0.41
     runners
    0.41
    遠
    0.40
     funcionários
    0.40
     interfering
    0.40
    峄
    0.39
    耶
    0.39
    POSITIVE LOGITS
     lead
    0.65
    Lead
    0.63
    lead
    0.62
     Lead
    0.61
     filled
    0.49
    filled
    0.47
    Being
    0.44
    Filled
    0.42
     Being
    0.41
     Filled
    0.40
    Activations Density 0.001%

    No Known Activations