© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44355
    Prev
    Next
    INDEX
    Explanations

    Air Purifier, Ninja Foodi

    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
    }^{+},
    0.38
    neighbour
    0.38
    ━━
    0.37
     harbours
    0.36
     drob
    0.35
     autoridad
    0.35
    យ៉ាង
    0.35
    頻道
    0.35
     stifle
    0.34
    幼
    0.34
    POSITIVE LOGITS
    ına
    0.46
    ibilities
    0.43
    ানা
    0.43
    েন্ট
    0.42
    нага
    0.42
     celebrates
    0.41
     Maybe
    0.41
     ова
    0.41
    acious
    0.41
     negotiations
    0.40
    Activations Density 0.000%

    No Known Activations