INDEX

Explanations

instances in which someone advises, urges or cautions another regarding a topic or action

oai_token-act-pair · gemini-2.0-flash

pronouns

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

IGraphics

-0.62

WaitGroup

-0.56

migrationBuilder

-0.56

 CURIAM

-0.56

ciutto

-0.54

 gynnwys

-0.54

DoubleQuotes

-0.54

KommentareTeilen

-0.54

vermectin

-0.53

aarrggbb

-0.52

POSITIVE LOGITS

 them

0.90

us

0.88

him

0.70

me

0.67

 himself

0.59

 THEM

0.56

us

0.56

them

0.56

 anyone

0.54

 yourself

0.54

Activations Density 4.416%

instances in which someone advises, urges or cautions another regarding a topic or action

pronouns

No Comments

No Known Activations