© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48806
    Prev
    Next
    INDEX
    Explanations

    what it returns

    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_10_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
    })
    0.43
    -
    0.33
    }
    0.31
     })
    0.30
    .
    0.29
     controller
    0.29
     )}
    0.29
     thickness
    0.29
    }).
    0.29
     ayudar
    0.29
    POSITIVE LOGITS
    ل
    0.47
    К
    0.40
    ל
    0.39
    zuf
    0.38
    ホ
    0.38
    K
    0.38
    ल
    0.37
    er
    0.37
     Ма
    0.37
     Karite
    0.37
    Activations Density 0.086%

    No Known Activations