© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148851
    Prev
    Next
    INDEX
    Explanations

    read-only

    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_18_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
    t
    0.52
    al
    0.50
    ahan
    0.48
    koop
    0.48
    stup
    0.47
    der
    0.47
     وكانت
    0.46
    water
    0.44
    databind
    0.43
    laden
    0.43
    POSITIVE LOGITS
     protagonists
    0.59
     patrols
    0.55
     tuples
    0.54
     exempel
    0.53
    Გ
    0.53
    в
    0.52
     heirs
    0.51
     laborers
    0.51
     labores
    0.51
     pilots
    0.50
    Activations Density 0.000%

    No Known Activations