© 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. 122630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    كان
    0.71
    ί
    0.68
    és
    0.67
    aki
    0.67
    amen
    0.59
    <strong>
    0.57
    agen
    0.55
     ausges
    0.55
    ika
    0.53
     మరియు
    0.53
    POSITIVE LOGITS
    at
    0.98
    یت
    0.86
    𝗢
    0.86
    𝗬
    0.85
    𝗗
    0.82
    et
    0.80
     ک
    0.80
    دی
    0.80
    u
    0.77
    ல்
    0.77
    Activations Density 0.000%

    No Known Activations