© 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. 200312
    Prev
    Next
    INDEX
    Explanations

    software components

    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
    }}(\
    0.38
    nl
    0.38
     আই
    0.37
    ದಲ
    0.36
     ALG
    0.36
    TargetFramework
    0.35
    Chef
    0.35
     صرف
    0.35
     அறிக
    0.35
    <unused94>
    0.35
    POSITIVE LOGITS
    𝓂
    0.45
    inserted
    0.44
    थिक
    0.44
    PathParam
    0.42
    patan
    0.40
    женных
    0.40
     எனக்
    0.39
    ret
    0.39
     stratum
    0.38
     superman
    0.38
    Activations Density 0.003%

    No Known Activations