© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193777
    Prev
    Next
    INDEX
    Explanations

    sensor, tag, operator

    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_27_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
     minimo
    0.44
    絵
    0.43
    の意味
    0.42
    Shell
    0.41
     চিত্রক
    0.41
    VCT
    0.39
    ANC
    0.39
    Instant
    0.39
    unavailable
    0.39
    BTS
    0.38
    POSITIVE LOGITS
     spongy
    0.40
    ilfe
    0.39
     ire
    0.37
    loon
    0.37
     स्था
    0.36
     containing
    0.35
    ]&
    0.35
    дко
    0.35
     loosened
    0.34
     underscores
    0.34
    Activations Density 0.000%

    No Known Activations