© 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. 44843
    Prev
    Next
    INDEX
    Explanations

    username after comment

    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
    Includes
    0.44
    זו
    0.43
    やり
    0.42
    敺
    0.41
    SIDE
    0.40
     זו
    0.40
     grouping
    0.40
     specifics
    0.39
     mengatasi
    0.39
     studying
    0.39
    POSITIVE LOGITS
     देता
    0.43
    reasonable
    0.42
     compensated
    0.41
    atá
    0.40
    ਫ਼
    0.40
    电设备
    0.40
     ២
    0.39
    atum
    0.39
     아주
    0.39
    atina
    0.39
    Activations Density 0.000%

    No Known Activations