INDEX

Explanations

mathematical notation, theorems, and academic publications

oai_token-act-pair · gemini-2.0-flash

mathematical proofs

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

 GenerationType

-0.77

 AssemblyCulture

-0.75

 jScrollPane

-0.69

 ProtoMessage

-0.63

Билгалдахарш

-0.60

ExecuteReader

-0.60

setVerticalGroup

-0.60

 FetchType

-0.59

 Italijani

-0.59

CloseOperation

-0.59

POSITIVE LOGITS

ieuses

0.54

PerformLayout

0.48

ruimte

0.44

Prog

0.44

variety

0.44

 COMERC

0.43

 algebra

0.43

ometric

0.42

sum

0.41

ayaquil

0.41

Activations Density 11.861%

mathematical notation, theorems, and academic publications

mathematical proofs

No Comments

No Known Activations