INDEX

Explanations

mentions of animals, especially sharks, locations, or mentions taking a photograph.

oai_token-act-pair · gemini-2.0-flash

animals

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

Gim

-0.57

enfone

-0.50

قایناقلار

-0.49

 damn

-0.49

Exp

-0.49

 cong

-0.48

 balanceOf

-0.47

asin

-0.47

Manbalar

-0.47

strix

-0.47

POSITIVE LOGITS

onAttach

0.71

 متعلقه

0.71

Demikian

0.61

tanleria

0.60

 виправивши

0.57

المشاركات

0.57

tráfico

0.56

hoppers

0.55

 lenker

0.55

 anvil

0.54

Activations Density 3.127%

mentions of animals, especially sharks, locations, or mentions taking a photograph.

animals

No Comments

No Known Activations