INDEX

Explanations

numbered steps in a set of instructions

oai_token-act-pair · gemini-2.0-flash

technical documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 disambiguazione

-0.60

 crease

-0.59

 pinch

-0.57

 undone

-0.57

pinch

-0.57

tie

-0.56

 khai

-0.56

 fold

-0.55

protoimpl

-0.55

 tilt

-0.54

POSITIVE LOGITS

 doInBackground

0.60

ftagPool

0.57

 isEqualToString

0.56

 HasFactory

0.55

 EClass

0.53

 /\.(

0.52

forKey

0.52

 PackageManager

0.51

apatalk

0.51

formik

0.51

Activations Density 11.177%

numbered steps in a set of instructions

technical documentation

No Comments

No Known Activations