© 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. 8318
    Prev
    Next
    INDEX
    Explanations

    code fragments or computer language-related terms

    oai_token-act-pair · gemini-2.0-flash

    Programming and installation context

    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
     صوتيه
    -0.66
     Administrativna
    -0.63
    Personendaten
    -0.58
    standers
    -0.57
     gainera
    -0.55
    UrlResolution
    -0.54
    HideFlags
    -0.54
     Infórmanos
    -0.54
    μφωνα
    -0.53
    enchymal
    -0.51
    POSITIVE LOGITS
    …~
    0.64
    Przypisy
    0.56
     StringField
    0.55
    waitKey
    0.55
     IEnumerator
    0.53
     JDK
    0.50
    Билгалдахарш
    0.50
    navigationItem
    0.50
     cref
    0.50
    textTheme
    0.50
    Activations Density 6.068%

    No Known Activations