© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2604
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate that a policy or rule is being enacted

    oai_token-act-pair · gemini-2.0-flash

    terms related to changes and effects

    np_token-act-pair-logits · gpt-4o-mini

    effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    AsUp
    -0.55
     تانيه
    -0.48
    
    -0.48
    ChildScrollView
    -0.48
     []),
    -0.46
    idum
    -0.46
     diverging
    -0.45
     saites
    -0.44
    noli
    -0.43
     yüzde
    -0.43
    POSITIVE LOGITS
     effect
    1.54
    effect
    1.40
     into
    1.36
     Effect
    1.33
    Effect
    1.27
     EFFECT
    1.12
    into
    1.09
     efeito
    1.06
     Into
    1.05
     effects
    1.04
    Activations Density 2.089%

    No Known Activations