© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196041
    Prev
    Next
    INDEX
    Explanations

    Medium

    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_26_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
    iker
    0.41
    nosed
    0.41
    á
    0.40
    hoom
    0.40
    ioso
    0.38
    ча
    0.38
    raphics
    0.38
    aña
    0.38
    rill
    0.37
    واره
    0.37
    POSITIVE LOGITS
    頎
    0.38
     assimilate
    0.37
     borrow
    0.37
     kontinu
    0.37
     adsor
    0.36
     flush
    0.36
     của
    0.36
     disposing
    0.36
     allocate
    0.35
     পরিচালনা
    0.35
    Activations Density 0.002%

    No Known Activations