© 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. 84667
    Prev
    Next
    INDEX
    Explanations

    configuration options

    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_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
    whole
    0.44
    ForeColor
    0.44
    when
    0.41
    ft
    0.41
    때
    0.41
    comes
    0.40
     veio
    0.39
    know
    0.39
    нем
    0.38
    MBOL
    0.38
    POSITIVE LOGITS
    濩
    0.42
     diaphr
    0.42
    畩
    0.41
     sehingga
    0.41
    owanym
    0.41
     الطاقة
    0.40
    ナトリ
    0.40
    ogad
    0.40
    estomac
    0.39
     UITableViewCell
    0.38
    Activations Density 0.000%

    No Known Activations