© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166828
    Prev
    Next
    INDEX
    Explanations

    summarizing text into shorter versions

    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_31_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
     someplace
    0.47
     skiprows
    0.43
     Simpl
    0.40
    simpl
    0.40
     Elinor
    0.39
    Simpl
    0.38
    既
    0.38
     simplification
    0.38
    LTR
    0.36
    鼓励
    0.35
    POSITIVE LOGITS
     Pritchard
    0.42
    Absorption
    0.40
    inguistic
    0.40
    紧张
    0.39
     désir
    0.38
     jitter
    0.38
    齊
    0.38
    ᡠ
    0.38
    藝
    0.38
     absorption
    0.38
    Activations Density 0.005%

    No Known Activations