© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42252
    Prev
    Next
    INDEX
    Explanations

    input followed by variable names

    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_22_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
    E
    0.42
    ദാ
    0.39
    itelji
    0.39
    цы
    0.39
    图
    0.39
    Gi
    0.38
     transformation
    0.37
    !),
    0.37
    ATG
    0.36
    晒
    0.36
    POSITIVE LOGITS
    crom
    0.50
    🟥
    0.42
     zwięks
    0.42
    োষণ
    0.41
     მომ
    0.40
     Clifford
    0.40
    वीन
    0.39
    chromium
    0.39
    यां
    0.39
    webm
    0.38
    Activations Density 0.002%

    No Known Activations