© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44490
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ಅಂಶ
    0.51
    workbook
    0.47
    萼
    0.45
    ------+
    0.44
    cosine
    0.44
    люб
    0.44
    Cosine
    0.44
    }}\|
    0.43
    मूल
    0.42
    ὧ
    0.42
    POSITIVE LOGITS
     racing
    0.48
     Weak
    0.47
     NOT
    0.46
     Register
    0.46
    蚂
    0.46
     by
    0.44
     big
    0.44
     getting
    0.44
     maintaining
    0.44
     seeing
    0.44
    Activations Density 0.000%

    No Known Activations