© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81845
    Prev
    Next
    INDEX
    Explanations

    sand battery, sand filter, sand casting, sandstorm

    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_0_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
    5
    1.97
    ↵
    1.74
     to
    1.69
    6
    1.52
    야
    1.52
    ;
    1.39
    4
    1.35
    </h2>
    1.34
    9
    1.21
    라고
    1.19
    POSITIVE LOGITS
    ун
    1.49
    uk
    1.47
    و
    1.40
    1.39
    уна
    1.30
    ാ
    1.23
    ани
    1.21
    ू
    1.20
     Lupus
    1.18
    ма
    1.16
    Activations Density 0.002%

    No Known Activations