© 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. 219067
    Prev
    Next
    INDEX
    Explanations

    carbon sequestration

    np_max-act-logits · gemini-2.5-flash-lite
    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
     hadronic
    0.43
    휴
    0.39
     gradle
    0.38
    橑
    0.38
     circumferential
    0.38
    𝕘
    0.38
     தேதி
    0.38
    𒆜
    0.38
     Nelson
    0.37
    Edit
    0.37
    POSITIVE LOGITS
     Sequ
    0.58
    Sequ
    0.57
    sequ
    0.53
     Se
    0.51
    Se
    0.50
    seq
    0.50
     seq
    0.48
     SE
    0.48
     sequ
    0.47
     Seq
    0.46
    Activations Density 0.001%

    No Known Activations