© 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. 88214
    Prev
    Next
    INDEX
    Explanations

    Alhazen, houzz, azen, SSD

    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
    та
    0.92
    в
    0.87
    ел
    0.83
    𝚕
    0.79
    كم
    0.76
    𝚎
    0.73
    ל
    0.73
    ные
    0.72
    еди
    0.72
    ا
    0.72
    POSITIVE LOGITS
    }
    0.92
    <h2>
    0.84
     It
    0.78
    "
    0.77
    vil
    0.74
    hawk
    0.71
    )
    0.71
    vin
    0.69
    ]
    0.68
    vation
    0.67
    Activations Density 0.000%

    No Known Activations