© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206692
    Prev
    Next
    INDEX
    Explanations

    factors affecting it

    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_19_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
    ”，
    0.27
     今天
    0.26
     تړل
    0.26
    }}}+\
    0.26
    𝖔
    0.26
     wcex
    0.25
     AGAIN
    0.25
     swojej
    0.25
    ))+\
    0.25
    
    0.25
    POSITIVE LOGITS
    Set
    0.30
    Amb
    0.29
     wax
    0.29
    Factors
    0.28
    Task
    0.28
    Rick
    0.28
     factors
    0.26
    Rud
    0.26
    Phil
    0.25
     drivers
    0.25
    Activations Density 0.012%

    No Known Activations