© 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. 178558
    Prev
    Next
    INDEX
    Explanations

    concept | prototype | working | quality | right

    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_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
    қта
    0.27
    vable
    0.26
    არი
    0.26
     ሥራ
    0.25
     θε
    0.25
    pImage
    0.25
    墀
    0.24
     immagine
    0.24
     zeuden
    0.24
    ᓐ
    0.24
    POSITIVE LOGITS
    Next
    0.30
    appendChild
    0.30
     stuffs
    0.29
    ieniu
    0.28
    ident
    0.27
    ieren
    0.27
    Post
    0.26
     repeatedly
    0.26
     absorbs
    0.26
    stuffs
    0.26
    Activations Density 0.016%

    No Known Activations