© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98151
    Prev
    Next
    INDEX
    Explanations

    CFG scale: 7-12, 2M Karras

    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_14_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
     DEVELOP
    0.15
    阕
    0.14
     Lobkowicz
    0.14
    хии
    0.14
     gennaio
    0.14
     khen
    0.14
    ేష్
    0.13
    兟
    0.13
     wann
    0.13
    ות
    0.13
    POSITIVE LOGITS
    of
    0.14
     of
    0.13
     risked
    0.13
    標準
    0.12
    ansı
    0.12
    节省
    0.12
     வாக
    0.12
    id
    0.11
     defended
    0.11
    ütte
    0.11
    Activations Density 0.003%

    No Known Activations