© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149425
    Prev
    Next
    INDEX
    Explanations

    Factorio, city builders, industrial

    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_18_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
     Eurovision
    0.46
    gült
    0.46
    andfeel
    0.44
     soreness
    0.44
    к
    0.44
     sketchbook
    0.43
    schein
    0.42
     Maxime
    0.42
     Einwill
    0.42
    ၁
    0.41
    POSITIVE LOGITS
    Alert
    0.46
    VIS
    0.44
    nang
    0.44
     retirees
    0.44
    يطان
    0.43
     liquido
    0.42
     الله
    0.42
    atica
    0.42
    OMG
    0.42
    StateManager
    0.41
    Activations Density 0.002%

    No Known Activations