© 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. 5794
    Prev
    Next
    INDEX
    Explanations

    the verb "go" followed by short words like "to", and words related to duration of time.

    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
     go
    -1.30
     goes
    -1.27
     going
    -1.15
    goes
    -1.13
     went
    -1.13
     Going
    -1.09
    Going
    -1.08
    Go
    -1.08
    going
    -1.06
    go
    -1.05
    POSITIVE LOGITS
    ArrowToggle
    0.66
     to
    0.59
    afficheront
    0.54
    WithIOException
    0.51
    addPreferredGap
    0.51
    jooq
    0.50
    inafter
    0.50
     createSlice
    0.49
    Kaynakça
    0.49
    httphttps
    0.49
    Activations Density 3.171%

    No Known Activations