© 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
    2. Gemma-3-27B-IT
    3. 6-GEMMASCOPE-2-TRANSCODER-262K
    4. 134234
    Prev
    Next
    INDEX
    Explanations

    om, omni, OMR, OMM, OMMA, OMN

    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
     truce
    1.02
     perfusion
    0.99
     transaction
    0.98
    ุ
    0.98
    ю
    0.95
     tensile
    0.94
     conveyance
    0.94
     malicious
    0.93
     depolarization
    0.93
     principled
    0.91
    POSITIVE LOGITS
    im
    1.18
    O
    1.00
    },
    0.99
    ká
    0.99
    }:
    0.96
    and
    0.94
    }(
    0.94
     Ich
    0.94
    Hard
    0.93
    Number
    0.93
    Activations Density 0.000%

    No Known Activations