© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146012
    Prev
    Next
    INDEX
    Explanations

    disconcerting / hypothesizes

    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_0_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
     divulg
    1.80
    3
    1.66
    9
    1.65
    ↵↵
    1.55
    8
    1.53
     verific
    1.49
    6
    1.49
    4
    1.45
    2
    1.38
    -
    1.30
    POSITIVE LOGITS
    ről
    1.43
    લ
    1.37
    u
    1.32
    ール
    1.31
    ř
    1.30
    یک
    1.27
    ால்
    1.27
     этом
    1.27
    л
    1.25
    ěl
    1.22
    Activations Density 0.000%

    No Known Activations