© 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
    2. Gemma-3-27B-IT
    3. 59-GEMMASCOPE-2-TRANSCODER-262K
    4. 149550
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    `);
    0.49
    ];
    0.48
    "".
    0.46
    ].
    0.45
    ]";
    0.45
    )—
    0.44
    .`);
    0.43
    .):
    0.42
    .].
    0.42
    ).\\
    0.42
    POSITIVE LOGITS
    മോ
    0.51
    <unused62>
    0.45
    مة
    0.44
    μων
    0.44
    мы
    0.43
     пять
    0.43
    мые
    0.43
    ming
    0.42
    ments
    0.41
    манов
    0.41
    Activations Density 0.004%

    No Known Activations