© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208375
    Prev
    Next
    INDEX
    Explanations

    pop culture 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_20_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
     تعین
    0.42
    了他的
    0.42
     Makin
    0.40
     자리
    0.39
    Power
    0.39
    থার
    0.38
     Josie
    0.38
    >().
    0.38
    ﺐ
    0.38
     considérable
    0.37
    POSITIVE LOGITS
     uncles
    0.38
     princesses
    0.38
     hormone
    0.38
     fertiliser
    0.37
     petrochemical
    0.37
     gives
    0.37
     plagues
    0.37
     hormonal
    0.36
     fluke
    0.36
     complies
    0.36
    Activations Density 0.001%

    No Known Activations