© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260402
    Prev
    Next
    INDEX
    Explanations

    sticking, adhere

    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_22_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
     stacking
    0.41
    uniti
    0.40
    }^{*}
    0.39
     mixing
    0.38
     auditing
    0.37
     redundancies
    0.37
    ἧ
    0.37
    辘
    0.37
    aternary
    0.36
    真实的
    0.36
    POSITIVE LOGITS
     übernommen
    0.49
     беше
    0.44
     Horowitz
    0.42
     entwickelte
    0.41
     biotech
    0.40
     doce
    0.40
     COMO
    0.39
     powsta
    0.39
    corto
    0.39
     kurze
    0.39
    Activations Density 0.002%

    No Known Activations