© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197236
    Prev
    Next
    INDEX
    Explanations

    espumadera, s'ambo

    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_4_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
     as
    1.16
    ка
    1.00
    𝟬
    0.93
    el
    0.92
    er
    0.92
     통해
    0.87
    го
    0.86
     I
    0.85
    ds
    0.83
    ri
    0.76
    POSITIVE LOGITS
    <0x0D>
    1.02
    ين
    0.98
    };
    0.95
    مي
    0.92
    </h2>
    0.91
    장
    0.89
    也是
    0.88
    и
    0.86
     powied
    0.85
    }).
    0.84
    Activations Density 0.001%

    No Known Activations