© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146021
    Prev
    Next
    INDEX
    Explanations

    social or public information

    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_0_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
     for
    1.45
     by
    1.43
    8
    1.43
     }.
    1.35
    ар
    1.34
    ]
    1.31
    ANG
    1.30
    :}
    1.27
    }
    1.27
    },
    1.26
    POSITIVE LOGITS
    ka
    1.46
    지를
    1.45
    ση
    1.34
    지가
    1.34
    y
    1.32
    크
    1.30
    한
    1.29
    च्या
    1.27
    いました
    1.27
    一
    1.26
    Activations Density 0.000%

    No Known Activations