© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42678
    Prev
    Next
    INDEX
    Explanations

    semesters or academic years

    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_3_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
    ן
    0.64
     incre
    0.63
    
    0.63
    ر
    0.61
    す
    0.61
    𝟎
    0.61
    呷
    0.60
    رین
    0.60
     económicos
    0.58
    abbanti
    0.57
    POSITIVE LOGITS
    )
    0.86
    }
    0.77
    ك
    0.73
    )،
    0.68
    ET
    0.64
    ]
    0.64
    ED
    0.63
     playgrounds
    0.62
    ،
    0.62
    দের
    0.61
    Activations Density 0.000%

    No Known Activations