INDEX

Explanations

non-English phrases and characters

oai_token-act-pair · gemini-2.0-flash

Foreign language/names

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

 enfans

-0.65

 étoit

-0.63

 avoient

-0.61

 auroit

-0.56

bibinfo

-0.56

 ſta

-0.56

 fidé

-0.54

Efq

-0.54

běh

-0.54

 exile

-0.54

POSITIVE LOGITS

 surla

0.68

 PublicKey

0.59

 gesso

0.58

 mxArray

0.56

PerformLayout

0.55

AccessorTable

0.55

 FirebaseAuth

0.55

RenderAtEndOf

0.54

Quran

0.54

WithEmail

0.53

Activations Density 0.820%

non-English phrases and characters

Foreign language/names

No Comments

No Known Activations