© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127361
    Prev
    Next
    INDEX
    Explanations

    caves and underground formations

    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_37_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
    कोष्ठ
    0.44
     stockholder
    0.38
    ettore
    0.38
    atsby
    0.37
    Wiley
    0.37
     widget
    0.36
    \;\
    0.35
    ებენ
    0.35
    ◄
    0.34
     Jaff
    0.34
    POSITIVE LOGITS
     cave
    1.37
     caves
    1.22
    cave
    1.09
     Cave
    1.05
     Caves
    1.02
    Cave
    1.02
     caver
    1.00
     cavern
    0.86
    洞
    0.83
     underground
    0.77
    Activations Density 0.002%

    No Known Activations