© 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. 44163
    Prev
    Next
    INDEX
    Explanations

    items(), component(), error, hasNext()

    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
    дето
    0.10
     vials
    0.10
    vastatin
    0.10
     interfere
    0.10
     enteral
    0.10
     exchange
    0.09
     exchanges
    0.09
    娘
    0.09
    utzerklärung
    0.09
     Fourth
    0.09
    POSITIVE LOGITS
     responsable
    0.10
     responsabile
    0.10
    댑
    0.10
    є
    0.09
    ಖ
    0.09
     consapevole
    0.09
    ह्म
    0.09
     Harvest
    0.09
    <start_of_image>
    0.09
     responsible
    0.09
    Activations Density 0.000%

    No Known Activations