© 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. 167005
    Prev
    Next
    INDEX
    Explanations

    near

    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
     range
    0.56
     RANGE
    0.51
    range
    0.47
    Range
    0.45
     Range
    0.45
     left
    0.43
    좌
    0.42
    RANGE
    0.42
     диапазо
    0.38
     \%)$.
    0.37
    POSITIVE LOGITS
     Near
    0.61
     near
    0.54
    Near
    0.50
    near
    0.48
     meeting
    0.44
     közel
    0.44
    യുള്ള
    0.44
    NEAR
    0.42
     NEAR
    0.42
    στ
    0.41
    Activations Density 0.002%

    No Known Activations