© 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
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179080
    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_24_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
     delays
    0.47
    雬
    0.46
    <0xBA>
    0.45
     ditth
    0.44
     هيكون
    0.44
    চ্ছিলেন
    0.44
     dolazi
    0.44
    ፣
    0.44
     بيكون
    0.43
     pharma
    0.43
    POSITIVE LOGITS
     Бен
    0.46
     செல்சிய
    0.43
    tering
    0.43
    zn
    0.42
    ste
    0.41
    trust
    0.40
    sax
    0.40
    do
    0.39
    steiner
    0.38
     அறிய
    0.38
    Activations Density 0.000%

    No Known Activations