© 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. 8654
    Prev
    Next
    INDEX
    Explanations

    sentence fragments in the middle of paragraphs, possibly in broken English.

    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
     NUKAT
    -0.69
    يكب
    -0.56
     replying
    -0.56
     contemplating
    -0.55
     хотя
    -0.54
     handing
    -0.54
     associating
    -0.53
     embora
    -0.52
     unpacking
    -0.52
     mirando
    -0.52
    POSITIVE LOGITS
     】
    0.59
     AspNetCore
    0.58
    ंदीखरीदारी
    0.56
     nahilalakip
    0.53
     best
    0.52
     rate
    0.52
    Filmografie
    0.52
    PhysRevLett
    0.51
    GEBURTSDATUM
    0.50
     dose
    0.50
    Activations Density 13.619%

    No Known Activations