© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4630
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "able" or words containing "able" such as "reliable", possibly indicating a focus on capabilities or possibilities.

    oai_token-act-pair · gemini-2.0-flash

    able

    np_max-act · gemini-2.0-flash

    able

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    able
    -1.77
    ability
    -1.29
    a
    -1.27
    ade
    -1.15
    aus
    -1.10
    ah
    -1.06
    are
    -1.05
    away
    -1.05
    ably
    -1.02
    aren
    -1.01
    POSITIVE LOGITS
    tableFuture
    0.76
    tvguidetime
    0.63
    ari
    0.59
     Acorn
    0.59
    ApiModelProperty
    0.54
    ard
    0.54
     Abril
    0.53
    __((
    0.52
    AV
    0.52
    ioutil
    0.52
    Activations Density 5.031%

    No Known Activations