© 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. 167567
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation

    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
    -{\
    0.60
    /**
    0.43
    -${
    0.42
    -【
    0.40
    -\\
    0.40
    -|
    0.40
    -'+
    0.40
    -$\
    0.40
    -'
    0.39
    -',
    0.39
    POSITIVE LOGITS
     dodging
    0.61
     realising
    0.60
     tapping
    0.58
     searching
    0.58
     wishing
    0.58
     seeking
    0.57
     noticing
    0.57
     realizing
    0.56
     handing
    0.55
     tentando
    0.55
    Activations Density 0.000%

    No Known Activations