© 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. 45457
    Prev
    Next
    INDEX
    Explanations

    a number or measurement

    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
     nitrite
    0.44
     Polaribacter
    0.40
     spiked
    0.40
    豳
    0.40
     hacerlo
    0.39
    mia
    0.39
     raise
    0.38
    醅
    0.38
    Function
    0.38
    DMF
    0.37
    POSITIVE LOGITS
    ly
    0.42
     Governance
    0.42
     إل
    0.40
     [
    0.40
    챗
    0.40
     पूर्वक
    0.39
    尔
    0.38
     benign
    0.37
     Montessori
    0.37
     YouTube
    0.37
    Activations Density 0.000%

    No Known Activations