© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14431
    Prev
    Next
    INDEX
    Explanations

    catastrophic forgetting

    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_15_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
     Bibel
    0.26
     Gruppe
    0.25
     réduite
    0.25
     bool
    0.23
    اويه
    0.23
     Rien
    0.23
    لكتر
    0.23
    粲
    0.23
     Tenemos
    0.23
     seed
    0.22
    POSITIVE LOGITS
    res
    0.24
    al
    0.21
    anat
    0.21
    ana
    0.21
    ahmatullahi
    0.21
    adka
    0.21
    luž
    0.20
    ate
    0.20
    ok
    0.20
    また
    0.20
    Activations Density 0.002%

    No Known Activations