© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201516
    Prev
    Next
    INDEX
    Explanations

    graphite grade or sheets

    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_6_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
    ي
    1.30
    }
    1.28
    י
    1.26
    。
    1.19
    }.
    1.18
    ت
    1.18
     تحليل
    1.13
    i
    1.05
    }$.
    1.04
    נ
    1.04
    POSITIVE LOGITS
    ων
    0.86
    ong
    0.84
    ación
    0.84
    rias
    0.82
    imer
    0.82
    aker
    0.79
    рия
    0.79
    ens
    0.78
    old
    0.78
    ark
    0.77
    Activations Density 0.000%

    No Known Activations