© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87962
    Prev
    Next
    INDEX
    Explanations

    columns, Excel VBA, and markup references

    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
     ICD
    0.38
     gunakan
    0.37
    龧
    0.37
     abordagem
    0.36
    способ
    0.35
     disproportion
    0.35
     ¾
    0.35
     abord
    0.34
    Ӣ
    0.34
     digunakan
    0.34
    POSITIVE LOGITS
    enh
    0.37
    evaluation
    0.37
    Cloth
    0.36
    となって
    0.34
    Shake
    0.33
    ትክል
    0.33
    ánh
    0.32
     amended
    0.32
     ולא
    0.32
    vb
    0.32
    Activations Density 0.000%

    No Known Activations