© 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. 45247
    Prev
    Next
    INDEX
    Explanations

    line length config

    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
    nown
    0.40
    roid
    0.39
    room
    0.39
    னின்
    0.38
    ඈ
    0.38
    ニス
    0.38
    Likewise
    0.38
     stifle
    0.37
    毒
    0.37
    inden
    0.37
    POSITIVE LOGITS
     Chongqing
    0.44
     светло
    0.44
     Medicare
    0.42
     iets
    0.41
     erhöht
    0.41
     Alzheimer
    0.40
     cigars
    0.40
     Va
    0.39
    Medicare
    0.39
     அப
    0.39
    Activations Density 0.001%

    No Known Activations