© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215444
    Prev
    Next
    INDEX
    Explanations

    climate and data

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Clark
    0.40
    validated
    0.40
     stipulation
    0.38
     gal
    0.38
    Clark
    0.38
     LSM
    0.37
    iron
    0.37
    掘
    0.37
     желез
    0.36
     stew
    0.36
    POSITIVE LOGITS
     M
    0.53
    𝔪
    0.41
     columnas
    0.39
     Roxy
    0.39
     Bol
    0.39
     Feuer
    0.39
     Freunde
    0.39
    M
    0.38
     CORP
    0.38
    nolds
    0.38
    Activations Density 0.002%

    No Known Activations