© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6032
    Prev
    Next
    INDEX
    Explanations

    words related to actions or achieving goals

    oai_token-act-pair · gemini-2.0-flash

    allowing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     ProtoMessage
    -0.73
    MessageOf
    -0.59
     Administrativna
    -0.56
    WithIOException
    -0.55
     disambiguazione
    -0.55
    InitVars
    -0.52
     NSCoder
    -0.51
     MainAxisSize
    -0.51
    Clik
    -0.51
    englanniksi
    -0.51
    POSITIVE LOGITS
     having
    0.65
    让
    0.65
    having
    0.64
     allow
    0.62
     letting
    0.61
     allowing
    0.60
     Allowing
    0.60
     Allow
    0.59
     Having
    0.59
     Пусть
    0.59
    Activations Density 1.918%

    No Known Activations