© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167891
    Prev
    Next
    INDEX
    Explanations

    mobile homes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     fi
    0.38
    fi
    0.36
    ),'
    0.36
    وتين
    0.35
    seas
    0.35
    ಮಾರ
    0.34
    漳
    0.34
    ირ
    0.34
    𒂗
    0.34
     habit
    0.33
    POSITIVE LOGITS
     mobile
    2.23
     trailer
    2.17
     Mobile
    2.02
     Trailer
    2.00
    Mobile
    1.99
     trailers
    1.98
    mobile
    1.95
     मोबाइल
    1.90
    Trailer
    1.90
     MOBILE
    1.85
    Activations Density 0.001%

    No Known Activations