© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84158
    Prev
    Next
    INDEX
    Explanations

    historical evidence and mentions

    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_23_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
    ہنی
    0.26
    盗
    0.25
    SER
    0.24
     hilfreich
    0.24
    盜
    0.24
    JobID
    0.24
    Platform
    0.24
    Simulation
    0.23
    Capture
    0.23
    циям
    0.23
    POSITIVE LOGITS
     salicylic
    0.30
     వ
    0.29
    osal
    0.28
    asil
    0.27
    товый
    0.27
    ell
    0.27
    çi
    0.27
    am
    0.26
    oplastic
    0.26
     மட்டுமல்ல
    0.26
    Activations Density 0.007%

    No Known Activations