© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205446
    Prev
    Next
    INDEX
    Explanations

    fibonacci sequence

    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_25_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
     públicos
    0.29
     immunity
    0.29
     dakkh
    0.28
    राष्ट्र
    0.28
    bians
    0.28
    athletics
    0.28
     prêts
    0.27
    社
    0.27
    ಶಾ
    0.27
    abulous
    0.27
    POSITIVE LOGITS
     Simple
    0.25
     doom
    0.25
    ørte
    0.25
     Common
    0.24
     Axe
    0.24
    ◌
    0.24
     Polyp
    0.23
     Manual
    0.23
     Mono
    0.23
     Plain
    0.23
    Activations Density 0.008%

    No Known Activations