© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32700
    Prev
    Next
    INDEX
    Explanations

    selecting options or versions

    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_31_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
    סטר
    0.38
    ществ
    0.38
    যায়
    0.37
     steels
    0.36
    )>=
    0.35
    undle
    0.35
    acées
    0.33
    tsc
    0.33
     মার্
    0.32
     Martial
    0.32
    POSITIVE LOGITS
    Interestingly
    0.39
     apenas
    0.39
    ⿲
    0.38
     కా
    0.37
     الام
    0.37
    ГЭ
    0.37
     ternyata
    0.36
    나는
    0.36
    lanan
    0.35
    작
    0.35
    Activations Density 0.004%

    No Known Activations