INDEX

Explanations

code syntax and build script commands

oai_token-act-pair · gemini-2.0-flash

words related to "then"

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

 Exacts

-0.61

 Lordships

-0.57

Espèce

-0.54

Hauptartikel

-0.54

 nawr

-0.54

Crossref

-0.53

kloped

-0.53

iastes

-0.53

ulgação

-0.50

wezen

-0.50

POSITIVE LOGITS

 then

3.78

then

3.08

Then

2.97

 Then

2.91

 THEN

2.59

 entonces

2.55

THEN

2.44

 allora

2.34

 então

2.34

 dann

2.34

Activations Density 2.418%

code syntax and build script commands

words related to "then"

No Comments

No Known Activations