© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200880
    Prev
    Next
    INDEX
    Explanations

    shipboard

    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_6_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
    ם
    0.53
    ется
    0.45
    ד
    0.45
    ली
    0.41
    </h3>
    0.41
    ך
    0.41
     baker
    0.40
     digestion
    0.39
                  
    0.39
     cereal
    0.39
    POSITIVE LOGITS
    t
    0.59
    m
    0.56
    }')
    0.50
    ty
    0.49
    h
    0.48
    time
    0.48
    vés
    0.48
    g
    0.47
    on
    0.47
    name
    0.47
    Activations Density 0.000%

    No Known Activations