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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15364
    Prev
    Next
    INDEX
    Explanations

    words used in advertising, especially those that suggest capabilities or advanced technology

    oai_token-act-pair · gemini-2.0-flash

    Technology descriptions

    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
    Clik
    -0.82
    utta
    -0.61
     محفوظة
    -0.60
     easy
    -0.60
    Rüyada
    -0.58
    astify
    -0.57
     nakalista
    -0.53
     мәкал
    -0.52
     Seth
    -0.52
    Referències
    -0.52
    POSITIVE LOGITS
     Paglinawan
    0.65
     MainAxisSize
    0.53
    DockStyle
    0.52
    fml
    0.46
    tinyos
    0.46
     refroid
    0.45
    posedge
    0.44
    Попис
    0.44
     mérit
    0.44
     fourn
    0.44
    Activations Density 6.440%

    No Known Activations