© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 212003
    Prev
    Next
    INDEX
    Explanations

    percentages

    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_19_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
    ]".
    0.40
    ]",
    0.39
    İŞ
    0.38
     accused
    0.37
     yı
    0.37
    amplifier
    0.36
    アプリ
    0.36
     Phan
    0.35
    ร่
    0.35
     ampli
    0.34
    POSITIVE LOGITS
     Regierung
    0.39
    hnung
    0.38
     लो
    0.37
    gespr
    0.37
     Lloyd
    0.36
     використання
    0.36
     consideración
    0.36
    }}{\
    0.35
     consideration
    0.35
    த்தும்
    0.35
    Activations Density 0.001%

    No Known Activations