© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177949
    Prev
    Next
    INDEX
    Explanations

    Hydration and flexibility

    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_24_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
     terrazzo
    0.22
     activities
    0.22
     originates
    0.22
     prohibits
    0.21
     jewelry
    0.20
     unless
    0.20
    榖
    0.20
     inhibits
    0.20
     boulders
    0.20
    SETS
    0.20
    POSITIVE LOGITS
     хвати
    0.21
    ただ
    0.21
    呈
    0.20
    usize
    0.20
    erende
    0.19
     다만
    0.19
    ╼
    0.18
     टेस्टिंग
    0.18
    猶
    0.18
    Logistic
    0.18
    Activations Density 0.003%

    No Known Activations