INDEX

Explanations

words associated with social behaviors or scientific writing

oai_token-act-pair · gemini-2.0-flash

Many

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 utafitiHapana

-0.52

idigung

-0.48

บัติ

-0.46

Datuak

-0.46

CMYK

-0.44

Fq

-0.42

pieler

-0.41

 Eraser

-0.40

riwal

-0.40

atists

-0.40

POSITIVE LOGITS

 lots

1.91

 Lots

1.74

Lots

1.73

 many

1.73

lots

1.59

many

1.59

 muchos

1.57

 alot

1.54

 LOTS

1.52

 banyak

1.52

Activations Density 3.182%

words associated with social behaviors or scientific writing

Many

No Comments

No Known Activations