© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196342
    Prev
    Next
    INDEX
    Explanations

    Sol/Sal prefixes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    WAN
    0.53
    wan
    0.48
    വന്‍
    0.48
    imon
    0.46
    construct
    0.45
    amon
    0.45
    van
    0.43
    积
    0.42
     VAN
    0.41
    mon
    0.41
    POSITIVE LOGITS
     biot
    0.44
     Verte
    0.42
     Greenfield
    0.41
    UpdateChoice
    0.39
     Aquino
    0.39
     Salmon
    0.39
    而是
    0.39
    autista
    0.38
    reetype
    0.38
    Benzoimidazol
    0.38
    Activations Density 0.001%

    No Known Activations