© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208981
    Prev
    Next
    INDEX
    Explanations

    plugging into

    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_10_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
    ight
    0.42
    ach
    0.39
    ى
    0.34
    emps
    0.34
    create
    0.33
    ess
    0.33
    oting
    0.32
    voir
    0.32
    out
    0.32
    ği
    0.32
    POSITIVE LOGITS
    >
    0.44
     were
    0.43
    ی
    0.43
    사
    0.41
    یی
    0.38
    ཱ
    0.38
    t
    0.37
     reviewers
    0.37
     choirs
    0.37
    ের
    0.36
    Activations Density 0.003%

    No Known Activations