© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4051
    Prev
    Next
    INDEX
    Explanations

    words related to languages and the use of verbs

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    np_max-act · gemini-2.0-flash

    word endings

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     متعلقه
    -0.83
     الرياضيه
    -0.74
    bootstrapcdn
    -0.72
     nakalista
    -0.72
    rítica
    -0.71
    脚注の使い方
    -0.66
    DeleteBehavior
    -0.65
     arrivo
    -0.65
    ########.
    -0.64
     StatelessWidget
    -0.64
    POSITIVE LOGITS
    ällningar
    0.50
    rippa
    0.46
    SOUNDBITE
    0.45
    billy
    0.44
    ----------------
    0.44
    elk
    0.43
     Chwiliwch
    0.43
     standout
    0.43
    :-
    0.43
    genza
    0.42
    Activations Density 15.321%

    No Known Activations