© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131530
    Prev
    Next
    INDEX
    Explanations

    Hofbräuhaus

    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_1_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
    ل
    1.12
    nian
    0.96
    konstru
    0.96
    lam
    0.95
    vita
    0.95
    lte
    0.92
    ls
    0.90
    csak
    0.90
    mur
    0.90
    cales
    0.89
    POSITIVE LOGITS
     was
    1.29
    기
    1.29
    ные
    1.16
     is
    1.15
    の
    1.13
    의
    1.13
    ्ले
    1.11
     can
    1.10
     has
    1.09
     purifier
    1.06
    Activations Density 0.000%

    No Known Activations