© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1490
    Prev
    Next
    INDEX
    Explanations

    call out, call me, call them

    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_39_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
     đóng
    0.37
    ਰਾ
    0.37
     വയ
    0.37
    mediaDevices
    0.37
     bij
    0.35
     devised
    0.35
     jag
    0.34
    窃
    0.34
    ęd
    0.34
    件事
    0.34
    POSITIVE LOGITS
     conditions
    0.44
     upon
    0.44
     условия
    0.43
     call
    0.41
     조건
    0.40
     aggregates
    0.40
     Call
    0.40
     condiciones
    0.40
     NRS
    0.39
     generation
    0.39
    Activations Density 0.014%

    No Known Activations