© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170253
    Prev
    Next
    INDEX
    Explanations

    needed

    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_56_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
     э
    1.64
    エ
    1.51
     Es
    1.35
     Э
    1.28
    Es
    1.26
     에
    1.25
     エ
    1.22
    のエ
    1.21
    Э
    1.20
    E
    1.20
    POSITIVE LOGITS
     needed
    0.85
    needed
    0.72
     Needed
    0.64
    Needed
    0.63
     necesitaba
    0.50
    SES
    0.47
     GES
    0.46
     nodig
    0.44
     Tess
    0.44
    NEEDED
    0.44
    Activations Density 0.014%

    No Known Activations