© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250044
    Prev
    Next
    INDEX
    Explanations

    former

    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
    ʹ
    0.82
    ᾽
    0.68
    ’
    0.65
    ′
    0.60
    ′-
    0.59
    ΄
    0.59
    ′,
    0.57
    ِّ
    0.55
    '
    0.55
    ׳
    0.55
    POSITIVE LOGITS
     former
    2.16
     Former
    2.08
    Former
    2.05
    former
    2.02
     býval
    1.60
     ehemaligen
    1.59
     সাবেক
    1.50
     ehemalige
    1.49
     бывшего
    1.49
     ehemal
    1.48
    Activations Density 0.003%

    No Known Activations