© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162166
    Prev
    Next
    INDEX
    Explanations

    jacked into, C.J.L

    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_2_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
    1
    1.98
    5
    1.70
    3
    1.62
    6
    1.50
    in
    1.49
    )
    1.45
    9
    1.37
    ↵
    1.24
    4
    1.23
    7
    1.18
    POSITIVE LOGITS
    م
    1.76
    ری
    1.39
    p
    1.37
    ह
    1.25
    ेट
    1.23
    ம்
    1.20
    مپ
    1.20
    й
    1.16
    ی
    1.14
    خ
    1.13
    Activations Density 0.000%

    No Known Activations