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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141072
    Prev
    Next
    INDEX
    Explanations

    life's story

    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_12_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
    t
    0.54
    ?")
    0.49
    ძლიათ
    0.48
     mocha
    0.46
    ijnlijk
    0.46
    గా
    0.43
     resurrect
    0.42
    perplexity
    0.42
    LevelLinking
    0.42
     bustle
    0.41
    POSITIVE LOGITS
    ל
    0.70
    า
    0.61
    ב
    0.55
    ד
    0.55
    INE
    0.54
    מ
    0.54
    am
    0.51
    тового
    0.51
    òng
    0.50
     l
    0.50
    Activations Density 0.000%

    No Known Activations