© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32095
    Prev
    Next
    INDEX
    Explanations

    keep up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    ান
    0.51
     měl
    0.41
     měla
    0.39
    at
    0.38
     avaient
    0.37
    ਾ
    0.36
     acht
    0.36
     pernah
    0.36
     obligé
    0.35
    RULES
    0.35
    POSITIVE LOGITS
     is
    0.50
     are
    0.50
    是
    0.46
    は
    0.46
    س
    0.45
    ५
    0.43
    נ
    0.42
    غ
    0.40
    는
    0.40
    ny
    0.39
    Activations Density 0.001%

    No Known Activations