© 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. 12112
    Prev
    Next
    INDEX
    Explanations

    places where the text is using unusual punctuation and sentence structure

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · 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
    prepareStatement
    -0.55
     Polsek
    -0.54
    HasForeignKey
    -0.53
    {?>
    -0.53
    ConstraintMaker
    -0.52
     Mane
    -0.50
    RTDA
    -0.50
    ISPR
    -0.50
     المكتبه
    -0.50
    PMC
    -0.50
    POSITIVE LOGITS
     étoit
    0.52
    Nay
    0.50
     Infir
    0.49
     misure
    0.48
     eût
    0.48
     porcelaine
    0.48
     Whence
    0.47
     Cæsar
    0.47
     canina
    0.47
     kumpulan
    0.47
    Activations Density 9.408%

    No Known Activations