© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217883
    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_47_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
    database
    0.42
     electrop
    0.37
    fallen
    0.37
    ])]
    0.36
    Oj
    0.36
    Titan
    0.36
     surviv
    0.36
    ldap
    0.35
     imperatives
    0.35
    勒
    0.35
    POSITIVE LOGITS
    忽
    0.39
     mé
    0.38
    みな
    0.37
     descanso
    0.37
     REST
    0.36
    म्र
    0.36
     needlessly
    0.35
     ಸ್ವ
    0.35
    }_{-
    0.35
     ઉ
    0.34
    Activations Density 0.000%

    No Known Activations