INDEX

Explanations

mentions of companies or inventions

oai_token-act-pair · gemini-2.0-flash

Pool chemicals

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

 ſame

-0.54

ành

-0.54

 whoſe

-0.54

ρόν

-0.53

 himſelf

-0.51

subfigure

-0.50

 ſtate

-0.50

 preſent

-0.49

 disparu

-0.48

ſp

-0.48

POSITIVE LOGITS

 Pool

0.67

 pool

0.65

 chemical

0.64

 POOL

0.61

pool

0.61

Pool

0.59

chemical

0.57

Diwedd

0.57

 Chem

0.54

 Chemical

0.54

Activations Density 1.140%

mentions of companies or inventions

Pool chemicals

No Comments

No Known Activations