© 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. 133008
    Prev
    Next
    INDEX
    Explanations

    Inner Outer

    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
    лда
    0.42
    <unused96>
    0.41
    ющими
    0.36
    ceiver
    0.35
    aville
    0.35
     Silence
    0.35
    ющих
    0.35
     haven
    0.35
     fringe
    0.35
     Pop
    0.34
    POSITIVE LOGITS
    ritz
    0.41
     az
    0.41
    𝓰
    0.39
     sam
    0.38
     ক্লান্ত
    0.38
    Kos
    0.38
    }^{+\
    0.37
    փ
    0.37
    Sam
    0.37
    股
    0.37
    Activations Density 0.002%

    No Known Activations