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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167685
    Prev
    Next
    INDEX
    Explanations

    J

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    льным
    0.40
     adimensional
    0.39
    вто
    0.39
    eggi
    0.37
    ))){
    0.36
    ईआरटी
    0.36
    ർത്ത
    0.36
    以往
    0.36
     asientos
    0.36
    decimal
    0.35
    POSITIVE LOGITS
     jy
    0.50
     j
    0.50
    จ
    0.50
     χ
    0.45
    j
    0.45
    ж
    0.44
     ج
    0.44
     Jain
    0.44
     jl
    0.42
     jh
    0.42
    Activations Density 0.000%

    No Known Activations