© 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. 8455
    Prev
    Next
    INDEX
    Explanations

    what appears to be proper nouns or names, especially those with "eber"-looking sequences

    oai_token-act-pair · gemini-2.0-flash

    Shishi Red

    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
     مشين
    -0.71
    ValueStyle
    -0.69
    Rptr
    -0.68
    CloseOperation
    -0.68
    verwijspagina
    -0.68
    rungsseite
    -0.67
    EndInit
    -0.66
    kháu
    -0.65
     consultato
    -0.64
    HomeAsUpEnabled
    -0.60
    POSITIVE LOGITS
     réfrig
    0.47
    tuta
    0.46
    Autoritní
    0.45
    gez
    0.45
    Personendaten
    0.44
    Zi
    0.43
    TEX
    0.43
    IKAN
    0.42
    UTES
    0.42
    utia
    0.41
    Activations Density 1.735%

    No Known Activations