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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10604
    Prev
    Next
    INDEX
    Explanations

    historical academic sources

    oai_token-act-pair · gemini-2.0-flash

    historical references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     remb
    -0.45
    ئ
    -0.42
     men
    -0.42
    gamesh
    -0.40
    verlag
    -0.40
     sac
    -0.38
    Verlag
    -0.37
    كتاب
    -0.37
    Portale
    -0.35
    пря
    -0.35
    POSITIVE LOGITS
    URLException
    0.88
    ArrowToggle
    0.77
    enderror
    0.77
    BufferException
    0.73
     تانيه
    0.72
    HostException
    0.70
    AddTagHelper
    0.69
    abetes
    0.69
    __:
    0.68
     rarity
    0.68
    Activations Density 0.401%

    No Known Activations