© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33360
    Prev
    Next
    INDEX
    Explanations

    metrics telemetry

    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
     radon
    0.44
    河
    0.40
     Connect
    0.39
     Ti
    0.39
     prefer
    0.38
     gravit
    0.38
     লাই
    0.38
     Prefer
    0.37
    मॉडल
    0.37
     GAN
    0.36
    POSITIVE LOGITS
     facility
    0.46
     dons
    0.38
    facility
    0.37
    奠
    0.37
    acterium
    0.36
     équipements
    0.36
     recklessly
    0.35
    ErrorKind
    0.34
     인수
    0.34
    첨
    0.34
    Activations Density 0.075%

    No Known Activations