INDEX

Explanations

words related to causing or stopping destruction

oai_token-act-pair · gemini-2.0-flash

what

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

webElementXpaths

-0.77

 cherchés

-0.76

addCriterion

-0.67

findpost

-0.66

 tartalomajánló

-0.65

oredCriteria

-0.65

parsedMessage

-0.62

 متعلقه

-0.60

RTEX

-0.59

PreferredItem

-0.58

POSITIVE LOGITS

 what

1.70

what

1.36

 What

1.16

What

1.16

WHAT

1.02

 something

1.02

 WHAT

1.02

 whats

0.99

 thing

0.96

 aquilo

0.93

Activations Density 1.320%

words related to causing or stopping destruction

what

No Comments

No Known Activations