INDEX

Explanations

language around helping with a task, or changing outcomes.

oai_token-act-pair · gemini-2.0-flash

expressing possibility

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

Stayed

-0.56

ยว

-0.50

htub

-0.46

 habet

-0.46

 Constitucional

-0.46

tagHelper

-0.45

intellij

-0.45

rej

-0.45

íté

-0.45

Hozzáférés

-0.44

POSITIVE LOGITS

 help

0.97

 helps

0.89

help

0.81

 HELP

0.79

 Help

0.79

Help

0.79

 giúp

0.78

helps

0.77

 assist

0.75

 помогают

0.75

Activations Density 1.707%

language around helping with a task, or changing outcomes.

expressing possibility

No Comments

No Known Activations