© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205041
    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_25_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
     formalized
    0.40
    ally
    0.38
    consciously
    0.38
    atted
    0.38
    !}
    0.37
     విధంగా
    0.36
    oph
    0.36
    adakan
    0.36
    proclaimed
    0.36
    account
    0.35
    POSITIVE LOGITS
     quaternion
    0.42
     help
    0.39
     intre
    0.38
     bre
    0.38
     leucine
    0.38
    Raven
    0.37
     value
    0.36
     collagen
    0.35
    CEL
    0.35
    𝐷
    0.35
    Activations Density 0.000%

    No Known Activations