© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 131420
    Prev
    Next
    INDEX
    Explanations

    requests for information

    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
     ARTS
    0.47
     Arts
    0.43
    atorio
    0.41
     arts
    0.40
    チナ
    0.40
    Arts
    0.40
     Baton
    0.38
    誤
    0.37
    áln
    0.37
     تتم
    0.36
    POSITIVE LOGITS
    agi
    0.43
    ГЭ
    0.38
     الداله
    0.37
    poon
    0.36
    ensor
    0.36
     rusk
    0.35
    тли
    0.35
    aga
    0.35
    jach
    0.35
    rak
    0.35
    Activations Density 0.001%

    No Known Activations