© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208293
    Prev
    Next
    INDEX
    Explanations

    number of balls

    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_25_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
    }=\
    0.21
     кос
    0.20
    };\
    0.19
     انب
    0.19
    Bapt
    0.19
     José
    0.18
     పరిస్థ
    0.18
     핸
    0.18
     robbery
    0.18
    Carl
    0.18
    POSITIVE LOGITS
     kvar
    0.22
     όσο
    0.21
     rundt
    0.21
     quanto
    0.21
     പ്രാ
    0.20
     februari
    0.20
    OGND
    0.20
    واد
    0.20
     originalmente
    0.20
    စိတ်အပိုင်း
    0.20
    Activations Density 0.004%

    No Known Activations