INDEX

Explanations

words associated with academic writing, science, technology, or math

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 صوتيه

-0.51

zugehen

-0.41

ölkerung

-0.40

tamen

-0.37

 associates

-0.37

ver

-0.37

ýchod

-0.37

<bos>

-0.36

érêt

-0.36

nictví

-0.35

POSITIVE LOGITS

StoryboardSegue

0.75

setVerticalGroup

0.72

AsUp

0.69

dersfield

0.68

elemField

0.67

makeText

0.65

dicionado

0.65

AutoScaleMode

0.64

 EdgeInsets

0.64

MessageTagHelper

0.61

Activations Density 42.632%

words associated with academic writing, science, technology, or math

No Comments

No Known Activations