© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4945
    Prev
    Next
    INDEX
    Explanations

    language about research surveys and rewards

    oai_token-act-pair · gemini-2.0-flash

    rewards and consequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     reward
    -2.39
     Reward
    -2.16
     rewards
    -2.14
    Reward
    -2.06
    reward
    -2.03
     rewarded
    -1.93
     Rewards
    -1.88
    rewards
    -1.75
    Rewards
    -1.74
     rewarding
    -1.68
    POSITIVE LOGITS
    VersionUID
    0.60
     հղումներ
    0.51
    ]=>
    0.45
    URLException
    0.43
    stringstream
    0.42
     Heer
    0.40
    Искәрмәләр
    0.40
    oa̍t
    0.40
    bable
    0.40
    Française
    0.40
    Activations Density 1.148%

    No Known Activations