© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92798
    Prev
    Next
    INDEX
    Explanations

    creative assistance

    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_11_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
    大
    0.59
    3
    0.58
    ের
    0.53
    un
    0.51
    メンテナンス
    0.51
    0
    0.50
    ロボ
    0.50
     सि
    0.49
    OM
    0.49
    することができます
    0.48
    POSITIVE LOGITS
     Abschnitt
    0.55
     _:
    0.53
    šana
    0.52
     SECTION
    0.51
     visualizing
    0.50
    pooling
    0.49
     parallèle
    0.49
    stilling
    0.49
     المجتمع
    0.48
    guide
    0.47
    Activations Density 0.011%

    No Known Activations