INDEX

Explanations

words and phrases that describe and relate to controversies or negative situations involving people and organizations.

oai_token-act-pair · gemini-2.0-flash

t

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

 Савезне

-0.56

InputBorder

-0.52

 Мексичка

-0.50

 betweenstory

-0.50

 متعلقه

-0.50

RegressionTest

-0.47

jsonwebtoken

-0.46

ezers

-0.45

 pertur

-0.44

دانشنامهٔ

-0.44

POSITIVE LOGITS

1.69

sul

1.00

0.91

0.89

0.88

getT

0.85

ｔ

0.85

mar

0.78

bes

0.77

su

0.75

Activations Density 3.246%

words and phrases that describe and relate to controversies or negative situations involving people and organizations.

t

No Comments

No Known Activations