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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88677
    Prev
    Next
    INDEX
    Explanations

    bath related items

    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_3_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
    ップ
    0.65
    ায়
    0.64
     acclaimed
    0.63
    つ
    0.62
    の一つ
    0.60
    のは
    0.60
    𝘁
    0.60
     midday
    0.59
     forested
    0.59
     ഇപ്പോൾ
    0.59
    POSITIVE LOGITS
    h
    1.11
    c
    1.04
    v
    0.88
    b
    0.86
    ير
    0.86
    d
    0.86
    3
    0.86
    e
    0.76
    f
    0.76
    ↵
    0.73
    Activations Density 0.000%

    No Known Activations