INDEX

Explanations

the word "you" followed by a contraction omitting the letter "o"

oai_token-act-pair · gemini-2.0-flash

"don't" or "never" statements

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

 slightest

-0.64

either

-0.56

Can

-0.56

 Puede

-0.55

 either

-0.55

expandindo

-0.54

 nessun

-0.52

 Either

-0.52

Either

-0.52

Anything

-0.51

POSITIVE LOGITS

 gotta

0.62

InputLabel

0.59

Koordinaten

0.58

 NavController

0.57

 phải

0.57

::$_

0.57

modelBuilder

0.56

reactstrap

0.55

pexpr

0.55

getSimpleName

0.54

Activations Density 0.252%

the word "you" followed by a contraction omitting the letter "o"

"don't" or "never" statements

No Comments

No Known Activations