© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53619
    Prev
    Next
    INDEX
    Explanations

    terrain and ground

    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_31_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
    inje
    0.38
     kW
    0.37
    *}$
    0.37
     Issled
    0.36
    ✼
    0.36
    స్య
    0.35
    Liquid
    0.35
     universe
    0.35
     va
    0.34
    hon
    0.34
    POSITIVE LOGITS
     땅
    0.57
    地面
    0.56
    terrain
    0.55
    Terrain
    0.54
     Terrain
    0.54
     terrain
    0.52
    地形
    0.49
     floor
    0.48
     terrenos
    0.47
     زمین
    0.47
    Activations Density 0.046%

    No Known Activations