© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52632
    Prev
    Next
    INDEX
    Explanations

    adapting or personalizing

    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_55_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
     ITS
    0.39
    গ
    0.39
     prevalence
    0.36
     amorphous
    0.36
    野
    0.36
     domino
    0.35
     テ
    0.35
    доби
    0.34
     टे
    0.34
     Cui
    0.34
    POSITIVE LOGITS
    щению
    0.51
    umping
    0.44
    謦
    0.44
    ничный
    0.43
     केलेले
    0.43
    Reading
    0.42
    tering
    0.42
    ierter
    0.42
     Ignoring
    0.42
    Ignoring
    0.42
    Activations Density 0.000%

    No Known Activations