© 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. 178801
    Prev
    Next
    INDEX
    Explanations

    data and websites

    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
     Power
    0.40
    Power
    0.38
    யோ
    0.36
    profiss
    0.36
     smell
    0.36
    க்கே
    0.36
     पावर
    0.35
    萧
    0.35
     S
    0.35
     Chauhan
    0.35
    POSITIVE LOGITS
     বাস্ত
    0.40
    गतान
    0.39
    emakers
    0.39
    gis
    0.38
    eworld
    0.38
    নিষ
    0.38
    াবিশ
    0.38
     स्काउट
    0.38
    빗
    0.38
     glancing
    0.37
    Activations Density 0.000%

    No Known Activations