© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45900
    Prev
    Next
    INDEX
    Explanations

    machine vision, code

    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
    }
    0.97
    ä
    0.92
    ر
    0.84
    )
    0.81
    ]
    0.80
    N
    0.73
    ل
    0.70
    ق
    0.70
    K
    0.69
    ли
    0.68
    POSITIVE LOGITS
    𝓼
    0.83
    ເພດ
    0.81
    ną
    0.79
     problemi
    0.79
    lular
    0.76
    ların
    0.75
    aría
    0.75
    𝗺
    0.74
     борь
    0.74
    inę
    0.73
    Activations Density 0.002%

    No Known Activations