© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6735
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming syntax

    oai_token-act-pair · gemini-2.0-flash

    say "false"

    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
     Ahnung
    -0.59
    ArgsConstructor
    -0.57
    AndEndTag
    -0.56
    IsContent
    -0.56
    UserScript
    -0.55
    BeginContext
    -0.55
     EClass
    -0.53
    assertTrue
    -0.51
    featureID
    -0.51
    msgTypes
    -0.51
    POSITIVE LOGITS
     Nope
    1.12
    Nope
    1.09
     false
    1.01
     nope
    0.94
     False
    0.93
    false
    0.89
    Nein
    0.88
    False
    0.87
     FALSE
    0.84
    nope
    0.83
    Activations Density 2.212%

    No Known Activations