© 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. 126264
    Prev
    Next
    INDEX
    Explanations

    floor plan

    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
     товар
    0.64
    टाइम
    0.59
     OBJECTTYPE
    0.58
    ang
    0.57
    ag
    0.57
     پڑے
    0.56
    ధాన
    0.56
    }))$
    0.56
    。）
    0.55
    沛
    0.55
    POSITIVE LOGITS
    ت
    1.09
    л
    0.96
    ת
    0.95
    т
    0.92
    ל
    0.89
    ן
    0.83
    t
    0.81
    𝐦
    0.79
    ल
    0.78
    ین
    0.75
    Activations Density 0.000%

    No Known Activations