© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118381
    Prev
    Next
    INDEX
    Explanations

    airport names

    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_27_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
    활
    0.32
    chid
    0.32
    aktif
    0.31
    ADAS
    0.31
    ®.
    0.31
    visor
    0.31
    CodeGen
    0.31
    appa
    0.30
    ®
    0.30
    ']].
    0.29
    POSITIVE LOGITS
     négoci
    0.36
     Ziel
    0.32
    জো
    0.32
     allerg
    0.31
     médias
    0.31
     mettre
    0.31
     झाला
    0.31
     sosyal
    0.30
     nasional
    0.30
     Of
    0.30
    Activations Density 0.002%

    No Known Activations