© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148653
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    j
    0.44
    го
    0.40
    拏
    0.40
    ㄦ
    0.40
    जग
    0.40
    ʒ
    0.39
    {
    0.39
    पुर
    0.38
     cob
    0.38
    ]);
    0.38
    POSITIVE LOGITS
     BlueprintName
    0.46
    arbeiten
    0.41
    ැනි
    0.40
    ন্যায়
    0.40
    Blueprint
    0.40
    كي
    0.40
     FormGroup
    0.39
     candidato
    0.39
    蓽
    0.39
    ാര്യ
    0.38
    Activations Density 0.000%

    No Known Activations