INDEX

Explanations

mathematical equations and expressions, especially those using dollar signs

oai_token-act-pair · gemini-2.0-flash

Scientific/technical writing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<?

-0.66

 onPostExecute

-0.65

 makeStyles

-0.61

abstractmethod

-0.60

InSection

-0.58

 houſe

-0.57

 gouver

-0.56

 larmes

-0.56

 HasFactory

-0.56

varande

-0.56

POSITIVE LOGITS

msgTypes

0.50

zzlies

0.49

 atoms

0.48

DebuggerNonUser

0.45

EXTERN

0.45

liers

0.43

 متح

0.43

hasMoreElements

0.43

 elements

0.42

TestTools

0.42

Activations Density 9.291%

mathematical equations and expressions, especially those using dollar signs

Scientific/technical writing

No Comments

No Known Activations