© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39149
    Prev
    Next
    INDEX
    Explanations

    bringing attention to details

    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_11_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
    á
    0.52
     sel
    0.51
     wiederum
    0.50
     varient
    0.50
     kér
    0.48
     miser
    0.48
     pas
    0.47
     seul
    0.46
     vérité
    0.46
    <0x8B>
    0.45
    POSITIVE LOGITS
    Примеча
    0.57
    NSW
    0.57
    cherry
    0.55
    COLOR
    0.55
    QC
    0.55
    devel
    0.54
    NaOH
    0.54
    Colour
    0.54
    ONLINE
    0.54
    РСР
    0.53
    Activations Density 0.009%

    No Known Activations