© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233691
    Prev
    Next
    INDEX
    Explanations

    blacksmith, forge, hammer, metalworking

    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_32_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
    ຜະລ
    0.38
     yì
    0.38
     craftsmen
    0.38
    }},
    0.38
     occupational
    0.37
     Nghi
    0.37
     Sony
    0.37
     উত্প
    0.37
     incre
    0.37
    }],
    0.36
    POSITIVE LOGITS
     tango
    0.40
     sco
    0.38
    genome
    0.37
     моро
    0.37
     சுகாதார
    0.37
     सेहत
    0.37
     raincoat
    0.37
     сп
    0.36
    ahoo
    0.36
     freezer
    0.36
    Activations Density 0.004%

    No Known Activations