© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3567
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and common words like 'it', 'is', and 'all'.

    oai_token-act-pair · gemini-2.0-flash

    go

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    хьтан
    -0.69
    tvguidetime
    -0.63
    rungsseite
    -0.63
    ukone
    -0.61
     kasarigan
    -0.60
     beginnetje
    -0.59
    IBarButtonItem
    -0.59
     виправивши
    -0.58
    :✨
    -0.57
    awaiter
    -0.57
    POSITIVE LOGITS
     goes
    1.87
     go
    1.80
     going
    1.71
     Going
    1.66
    Going
    1.65
     Goes
    1.61
     went
    1.59
    goes
    1.58
    going
    1.55
    Go
    1.48
    Activations Density 3.912%

    No Known Activations