INDEX

Explanations

symbols, equation references, and numbers

oai_token-act-pair · gemini-2.0-flash

citations or references

np_token-act-pair-logits · gpt-4o-mini

Non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

digans

-0.54

Personendaten

-0.48

ashed

-0.47

唇

-0.46

sibirsk

-0.46

PerformLayout

-0.45

 handleMessage

-0.45

 hearsay

-0.44

 silty

-0.44

<code>

-0.43

POSITIVE LOGITS

 محفوظة

0.62

 Drapeau

0.61

 Normdatei

0.60

FontOfSize

0.59

❋

0.58

igshid

0.56

MemoryWarning

0.54

ValueStyle

0.54

 JAXBElement

0.53

OrCreate

0.52

Activations Density 1.317%

symbols, equation references, and numbers

citations or references

Non-English words

No Comments

No Known Activations