© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5718
    Prev
    Next
    INDEX
    Explanations

    instantiating new objects

    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_39_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
     DCHECK
    0.37
    तोष
    0.34
    ProjectGuid
    0.33
     раствора
    0.33
    尺度
    0.33
    vorschau
    0.32
    ]!='
    0.31
    芸
    0.31
     पदार्थ
    0.31
    ູ້
    0.31
    POSITIVE LOGITS
     Cran
    0.39
     Java
    0.39
     java
    0.38
    jav
    0.36
     Maven
    0.35
    Java
    0.35
    java
    0.34
    Wra
    0.34
     JButton
    0.34
    jLabel
    0.34
    Activations Density 0.001%

    No Known Activations