© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3693
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by a verb, as well as words like 'can', 'could', 'may', and 'must'.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     track
    -0.68
     tracks
    -0.65
     pace
    -0.55
    jectures
    -0.54
    tracks
    -0.54
    track
    -0.54
     ordf
    -0.53
     pulito
    -0.52
    __":
    -0.52
     line
    -0.52
    POSITIVE LOGITS
    numerusform
    0.58
    SBATCH
    0.55
     AspNetCore
    0.54
     Normdatei
    0.53
    tvguidetime
    0.52
    parian
    0.51
     DialogInterface
    0.50
     يتيمه
    0.50
     Савезне
    0.50
    馃
    0.49
    Activations Density 4.879%

    No Known Activations