© 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. 36070
    Prev
    Next
    INDEX
    Explanations

    continuous learning

    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
     reductive
    0.35
     transposed
    0.35
     platforms
    0.34
     caustic
    0.33
    }]$,
    0.33
     reduced
    0.32
     Drupal
    0.32
    圾
    0.32
     dataframe
    0.32
    ​]]
    0.32
    POSITIVE LOGITS
    coproteins
    0.33
    聰
    0.31
     soient
    0.31
    aternion
    0.31
    <unused62>
    0.30
     setObject
    0.30
    𝐯
    0.30
    텨
    0.30
    newcommand
    0.30
     संकट
    0.30
    Activations Density 0.018%

    No Known Activations