© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12965
    Prev
    Next
    INDEX
    Explanations

    varied terms, with some emphasis on verbs and Serbian text snippets.

    oai_token-act-pair · gemini-2.0-flash

    mentions "himself"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -1.70
     themselves
    -1.66
    itself
    -1.55
    themselves
    -1.52
     ourselves
    -1.52
     yourselves
    -1.52
     herself
    -1.51
     yourself
    -1.41
    herself
    -1.33
     oneself
    -1.27
    POSITIVE LOGITS
    stackSize
    0.53
     посвящен
    0.50
    Географи
    0.49
    щен
    0.45
    čen
    0.44
    usen
    0.43
    чен
    0.43
    ąz
    0.43
    Breeding
    0.43
    шен
    0.42
    Activations Density 1.705%

    No Known Activations