© 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. 52571
    Prev
    Next
    INDEX
    Explanations

    code variable assignment

    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
     grind
    0.45
     Grind
    0.39
     deci
    0.38
     deceiving
    0.38
    磨
    0.38
     deceive
    0.37
     dental
    0.37
     fin
    0.36
     influence
    0.36
     spanish
    0.35
    POSITIVE LOGITS
    payers
    0.40
    haupt
    0.39
    BRID
    0.39
    ₂,
    0.39
     contestants
    0.39
     numerador
    0.37
    PLASMA
    0.36
     подойдет
    0.35
    paying
    0.35
     ayaa
    0.35
    Activations Density 0.004%

    No Known Activations