INDEX

Explanations

words related to research and data collection

oai_token-act-pair · gemini-2.0-flash

scientific studies

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 betweenstory

-0.95

iastes

-0.84

 snippetHide

-0.84

PreferredItem

-0.79

 propOrder

-0.74

Хьажоргаш

-0.73

 Савезне

-0.73

AddTagHelper

-0.73

 ModelExpression

-0.73

AccessorTable

-0.72

POSITIVE LOGITS

 regarding

0.82

 Regarding

0.80

 terhadap

0.75

Regarding

0.75

 towards

0.71

regarding

0.69

 hinsichtlich

0.66

 toward

0.66

 Concerning

0.65

 concernant

0.64

Activations Density 5.368%

words related to research and data collection

scientific studies

No Comments

No Known Activations