INDEX

Explanations

solving equations

np_max-act-logits · gemini-2.0-flash

text representing mathematical equations and systems

oai_token-act-pair · gemini-2.0-flash

mathematical equations and formulas

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 agents

-0.55

 ivelany

-0.55

 Agents

-0.55

therly

-0.52

agents

-0.52

Agents

-0.48

 équ

-0.48

 agent

-0.47

 LoggerFactory

-0.47

peutic

-0.47

POSITIVE LOGITS

ніципалі

0.69

 GenerationType

0.64

原始内容存档于

0.63

GIVEREF

0.60

addGap

0.59

addPreferredGap

0.57

Hauptartikel

0.57

 duele

0.54

AutoScaleMode

0.54

цездатний

0.53

Activations Density 4.516%

solving equations

text representing mathematical equations and systems

mathematical equations and formulas

No Comments

No Known Activations